StackFast FractWin Expert Brain

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context by confirming the packet is review-only and does not perform any autonomous actions, which aligns with and enhances the annotation hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the purpose and then adding behavioral context. Every sentence contributes meaning, and there is no unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description lacks parameter documentation and does not explain what the callback packet contains or when tenant_id is needed. For a tool with two parameters and no schema descriptions, this is insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has two parameters (call_id, tenant_id) with no descriptions, and the description does not mention any parameters. With 0% schema description coverage, the description fails to add meaning or clarify parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a human-review callback packet for one AI Receptionist call. It includes a specific verb ('Return') and resource ('callback packet'), but does not explicitly differentiate from siblings like ai_receptionist_review_queue or ai_receptionist_status within the description itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context that the packet is review-only and does not send SMS, place calls, or reply autonomously, which implies when not to use it. However, it does not explicitly state when to use this tool versus alternatives or provide exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint, establishing safe read behavior. The description adds value by specifying that returns include callback and SMS status where present and that identifiers are masked/audit-safe, which is not in annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that efficiently conveys the tool's purpose and output. It could benefit from an additional line to explain parameters, but as is, it is concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (which documents return values) and annotations covering safety, the description adequately covers tool behavior and output. The main gap is parameter semantics, but the tool is simple with only two optional parameters, so the description is mostly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate for missing parameter details, but it does not mention 'limit' or 'tenant_id' at all. The description focuses on output behavior (masked IDs, callback/SMS) but ignores input semantics, leaving the agent without guidance on how to use the parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists 'recent AI Receptionist call-loop receipts for human review' with specific detail about including callback and A2P-gated inbound SMS status. The phrase 'returns masked/audit-safe identifiers only' further clarifies the scope, distinguishing it from other AI Receptionist tools like ai_receptionist_callback_packet.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates the tool is for 'human review' of call-loop receipts, which provides clear context. However, it does not explicitly state when not to use it or mention alternative tools such as ai_receptionist_status. The purpose is clear but lacks exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds valuable context by listing exactly what data sources are read and that results are masked/status only, enhancing transparency beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single, concise sentence that front-loads the action and key details without any redundant or filler words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description adequately covers the input context (a call ID) and output nature (masked/status metadata). Minor gap: it could note that only one call ID is supported.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description partially compensates by identifying call_id as the key identifier ('for one AI Receptionist call ID'), but it does not clarify the optional tenant_id parameter or its purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verbs ('Read') and resources ('Desk ticket, CRM callback task, call-link receipt, A2P-gated inbound SMS posture') for one AI Receptionist call ID, clearly distinguishing it from sibling tools like ai_receptionist_callback_packet.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for reading status metadata for a single call ID, but does not explicitly state when to use it versus alternatives (e.g., ai_receptionist_callback_packet) or provide any when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the agent knows it is a safe read operation. The description adds valuable context by listing the specific audit fields accessible, which goes beyond the annotation. No contradictions or missing behavioral warnings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently communicates the tool's purpose and scope. Every word adds value, with no redundancy or unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers the purpose and read nature adequately, it lacks parameter explanations and usage guidance, which are partially compensated by the presence of an output schema and annotations. For a tool with 3 parameters and no schema descriptions, more detail would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 3 parameters with 0% description coverage. The description only mentions 'one tenant-scoped artifact', implying tenant_id is required, but does not explain the roles of draft_id or artifact_id. The agent must rely on parameter names alone, which may be insufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the verb 'Read' and lists specific data types (provenance, analyzer findings, gate status, etc.), clearly indicating what the tool does. It distinguishes itself from the sibling tool 'artifact_get' by focusing on audit details rather than the artifact itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'artifact_get' or 'audit_status'. It does not mention any prerequisites, exclusions, or use cases, leaving the agent to infer from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, suggesting no writes, but the description uses 'Create', implying a write operation. This contradiction confuses the tool's behavioral traits. The description does not clarify that the export receipt is generated without modifying the artifact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with two sentences that cover core functionality and boundary conditions without extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters (2 required), nested objects, and enums, the description fails to provide sufficient guidance for proper usage. It does not explain parameter relationships or the meaning of different target options, leaving the agent under-informed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides no explanation of parameters like format, target, draft_id, artifact_id, or target_config. Without additional context, an agent cannot understand how to set these parameters correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates an audited export receipt for approved artifacts or internal drafts, and distinguishes it from external publish, which remains separate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly mentions that external publish is handled separately and requires human approval, guiding when not to use this tool. However, it does not specify when to use alternatives like artifact_generate or artifact_save.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the readOnlyHint annotation by using 'generate,' implying a write operation. No further behavioral details (e.g., idempotency, rate limits, auth needs) are provided, and the contradiction undermines trust.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no filler, but its density may reduce clarity. It packs key features but could benefit from structure, e.g., listing constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite a complex tool with 16 parameters and an output schema, the description provides minimal context. It names some features but omits crucial details about required parameters, return format, or error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description should explain parameters, but it only hints at a few (tenant_id via 'tenant-scoped', artifact_type via 'artifact draft'). Most parameters, including lane, format, locale, audience, caller_type, variant_count, etc., remain unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it generates a 'governed, tenant-scoped artifact draft,' identifying the action and resource. However, it does not explicitly differentiate from sibling tools like artifact_refine or artifact_save, which might also produce drafts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, such as artifact_get for retrieval or artifact_refine for editing. No prerequisites or conditions for usage are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description contradicts annotations: annotations have readOnlyHint=true, implying no side effects, but 'refine' suggests mutation. The description does not clarify the actual behavior beyond preserving certain properties, and no additional behavioral context is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence. It is front-loaded with key information, but could benefit from a bit more structure to separate purpose from constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (11 parameters, 3 enums, no schema description coverage), the description is severely incomplete. It omits parameter explanations and does not discuss output despite the presence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description adds no meaning to any of the 11 parameters. It does not explain what each parameter does, which is critical for such a complex input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (refine), the object (existing artifact draft), and the constraints (preserving tenant boundary, provenance, MASK status, and approval posture). It distinguishes from sibling tools like artifact_generate (create) and artifact_save (save).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for refining existing drafts but lacks explicit guidance on when to use this tool versus alternatives. No when-not-to-use conditions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, but the description says 'approve/save', which implies writing. This contradiction severely undermines transparency. Additionally, the description adds 'Does not publish externally', but the overall behavioral profile is muddled by the contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very brief (two sentences) and front-loaded, but it omits critical details needed for correct tool invocation. Conciseness should not sacrifice completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, no schema coverage, and a contradiction between annotations and description, the description is insufficient. An output schema exists but is not shown; even so, the description does not cover parameter roles, behavior, or edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description provides no explanation of any parameters. Terms like 'tenant-scoped' hint at tenant_id but no specifics. The agent cannot infer parameter meanings or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('approve/save an artifact') and a specific purpose ('mark tenant-scoped learning-loop eligibility'). It provides a unique verb+resource combination, though it does not explicitly differentiate from siblings like artifact_generate or artifact_audit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The description implies usage for saving/approving artifacts and marking learning-loop eligibility, but lacks context about prerequisites, exclusions, or comparison with similar tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true. Description adds context on what is read (state, refs, ledger, links) but lacks behavioral details like permissions or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise but omits critical information about parameters. Could be expanded without losing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description only partially covers return content. Parameter semantics are absent, making it incomplete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain either parameter (tenant_id, audit_project_id), leaving them entirely ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it reads 'AI Stack Audit project state, deliverable refs, credit ledger, and Desk/CRM links', using a specific verb and resource. It distinguishes from siblings which focus on different domains (e.g., growthos, talent scout).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use vs alternatives. Siblings like artifact_get may also read project data but no comparison or exclusions provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds that the tool 'does not expose secrets', which is useful security context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no redundant information. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description fully covers the tool's purpose, behavior, and security implications. Given no parameters and presence of output schema, it is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so schema coverage is 100% trivially. Description adds context about the tool being a health check, which is sufficient for understanding what the tool does without parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'StackFast connector health/status check' which is a specific verb (check) and resource (connector health). No siblings exist, so differentiation is not required.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies usage for health checking, but does not explicitly state when to use or alternative tools. Since there are no sibling tools, the guidance is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds behavioral context beyond annotations: it states it 'never returns raw credentials' and specifies returned data types (service slugs, env/key aliases, categories, resolver guidance). This aligns with the readOnlyHint annotation without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, front-loading the purpose and usage. No redundant information is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema, the description sufficiently covers return values and behavior. It addresses use cases and what the tool does not do, making it complete for its complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not elaborate on the 'query' parameter beyond the schema, which already has 100% coverage with clear examples. Baseline 3 is appropriate as description adds minimal value for parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool discovers 'wallet-resolved credential service names and accepted aliases without exposing secret values.' This specific verb and resource clearly distinguishes it from sibling tools like 'fetch' or 'search' which deal with different data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: 'Use this when an agent is unsure whether a key exists, sees a key-not-found error, or needs the canonical getAgentKey(service) name.' It also implies not to use for retrieving secrets, covering both when and when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds no additional behavioral context beyond 'tenant-scoped' and 'generics', but does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise (one sentence), but overly generic. Conciseness is not valuable if it sacrifices clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 13 parameters, nested objects, and a non-trivial output schema, the description is too brief. It lacks details on return value, usage constraints, or how this relates to other estimator tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 15% schema description coverage, the description should compensate but does not. No parameters are explained in the description, leaving the agent to rely on a sparse schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the vague verb 'operate' instead of specifying 'search' or 'query', despite the tool name implying search. It does not distinguish from sibling tools like estimator_catalog_sources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description mentions 'generic estimator_* control-plane contract' but does not provide context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, but the description says 'Operate on,' which could imply write operations, potentially misleading an agent. No additional behavioral context beyond annotations is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but lacks structure. It conveys domain and scope but could be more efficiently organized without losing detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 params, nested objects, output schema), the description is severely incomplete. It fails to describe return values, parameter roles, or how to use the tool, leaving large gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 13 parameters and only 15% schema description coverage, the description omits almost all parameter meaning. The only hint is 'tenant-scoped,' which maps to tenant_id, but no other parameters are explained, leaving the agent with minimal guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as operating on tenant-scoped OCE Estimator/Appraiser catalog sources/items, including the StackFast storefront catalog, which distinguishes it from sibling estimator tools like estimator_catalog_search or estimator_estimate_* tools. However, it does not specify the exact operations (e.g., list, get, create) supported.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. The phrase 'through the generic estimator_* control-plane contract' is vague and does not offer actionable direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description says 'Operate' which is neutral, but the name implies a write operation (add line). Annotations declare readOnlyHint=true, contradicting the name. The description adds no behavioral context beyond the annotations, failing to resolve this confusion or disclose consequences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence but is overly broad and uninformative. It is concise in length but not in value; every part of the sentence is generic and fails to convey the tool's specific purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (13 parameters, nested objects, output schema exists), the description is severely incomplete. It does not state the primary action, required parameters, or what the tool returns. The output schema is not provided, but even if it were, the description fails to guide tool selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only 2 out of 13 parameters have descriptions in the schema (15% coverage). The description adds no parameter information, leaving most parameters completely undocumented. Baseline is low due to high parameter count and low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is extremely vague, stating 'Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.' It does not specify that the tool adds a line to an estimate, as the name suggests. The description is a generic list of entities, not a clear verb+resource statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. The description does not indicate when to use this tool versus sibling tools like estimator_estimate_update_line or estimator_estimate_create_draft. There is no mention of context, prerequisites, or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, indicating a safe read-only operation. However, the name 'convert_to_bid' and the verb 'Operate' imply a mutation, creating a contradiction. The description does not resolve this or disclose any behavioral traits such as required permissions, side effects, or return behavior, which is critical given the contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, but it is under-specified and lacks focus. While short, it is not concise because it uses vague language ('Operate on...') that adds little value. Every sentence should earn its place; this one does not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high parameter count (13), nested objects, and the presence of an output schema (not shown in description), the description is completely inadequate. It fails to explain what the tool does, what inputs are expected, or what output results. The tool is complex, and the description provides no meaningful context for understanding its functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 15%. The description adds no parameter information beyond the schema. Only two parameters (tenant_id and adapter_id) have brief descriptions in the schema. Many parameters are opaque objects with no description, and the description does not explain their roles. The tool's complexity demands more parameter clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts' is vague and does not state the specific action of converting an estimate to a bid. The name 'convert_to_bid' suggests a specific operation, but the description broadens it to generic 'operate', failing to clarify the tool's core purpose. It does not distinguish this tool from sibling tools like estimator_estimate_convert_to_invoice.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, constraints, or scenarios where this tool should or should not be used. The description lacks any usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds 'Review-gated' which clarifies access control, and 'does not write to accounting systems' reinforces the read-only nature. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, followed by constraints. No redundant words. Efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists, the description is too brief for a tool with 13 parameters, nested objects, and enums. It does not explain what 'prepare' entails, what 'QBO handoff' means, or how the 'review-gate' works.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 13 parameters and only 15% schema description coverage, the tool description provides no parameter-level details. It does not explain the purpose of 'line', 'lines', 'query', 'bridge', etc. The descriptions in the schema for 'adapter_id' and 'tenant_id' are present but are not supplemented in the tool description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Prepare' and the resource 'OCE Estimator/Appraiser document or QBO handoff contract'. It distinguishes from sibling tool 'estimator_estimate_convert_to_bid' by mentioning 'QBO handoff' and 'does not write to accounting systems'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions 'Review-gated; does not write to accounting systems', which implies when to use (after review, for document generation not final booking) but does not explicitly state when not to use or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare readOnlyHint=true, but the tool name implies a write operation ('create draft'). This contradiction is misleading. The description does not disclose behavioral traits beyond annotations, failing to resolve the inconsistency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence tries to cover many entity types and actions, making it verbose yet vague. It is not concise and lacks structure, such as bullet points or clear separation of concerns.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 13 parameters, many undocumented, and an existence of an output schema (not shown), the description fails to provide essential context. The tool's complexity is not addressed, leaving the agent with insufficient information to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 15% (2 out of 13 parameters have descriptions). The description adds no meaning to the many undocumented parameters like 'line', 'lines', 'query', etc. The tool needs to explain parameter purposes, especially nested objects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts' is vague and does not specify that this tool creates a draft estimate. The name suggests creation but the description covers many possible operations, lacking clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus sibling tools like estimator_estimate_add_line or estimator_estimate_export. The description does not indicate prerequisites or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true and idempotentHint=true, but the description adds no additional behavioral context. It is too vague to clarify read-only or export behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short sentence, but it is under-specified. Conciseness is good, but it sacrifices clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high parameter count, numerous siblings, and no output schema details, the description is entirely inadequate for an agent to use this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 13 parameters with only 15% description coverage. The description does not explain any parameters, leaving the agent to guess their meaning based solely on names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says 'Operate on...' which is vague and does not specify that this tool exports estimates. The name suggests export, but the description lists many entities without stating the action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus siblings. There are many similar estimator tools, but the description provides no context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds 'Review-gated' and 'does not write to accounting systems,' which aligns with and enriches the annotations. It provides useful context about the workflow without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with purpose. No wasted words. Could be improved by including parameter hints, but for its length it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 parameters, nested objects, output schema exists), the description is too sparse. It does not explain the document preparation process, parameter roles, or how the review gate works. Despite having an output schema, the agent needs more context to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Description coverage of input schema is only 15%, and the description does not compensate. It provides zero information about any of the 13 parameters, including those with enums or descriptions. The description fails to add meaning beyond the schema, leaving the agent without guidance on how to populate parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Prepare') and resource ('OCE Estimator/Appraiser document or QBO handoff contract'), which is clear. However, it does not explicitly mention 'progress invoice' despite the tool name, creating slight ambiguity. It distinguishes from sibling tools like estimator_estimate_convert_to_invoice by focusing on document preparation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides some guidance: 'Review-gated; does not write to accounting systems.' This implies a safe, draft-like usage. However, it does not explicitly state when to use this tool vs. alternatives (e.g., converting an estimate to invoice) or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds little beyond annotations. It lists resources but does not clarify behavior. Although annotations declare readOnlyHint=true, the tool name 'update' suggests mutation, creating confusion. The description does not address this discrepancy.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence but is too vague to be useful. It lists many entities without focusing on the tool's specific role, making it unhelpful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (13 parameters, nested objects, output schema), the description is grossly inadequate. It does not explain what the tool does, how to use it, or what output to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 15%, and the description contains no information about parameters. It does not explain the purpose or usage of any of the 13 parameters, leaving the agent with minimal guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is overly broad, stating 'Operate on tenant-scoped OCE Estimator/Appraiser drafts, lines, versions, documents, exports, and policy receipts.' It does not specify that this tool updates a line, as implied by the name. It also fails to distinguish from sibling tools like estimator_estimate_add_line.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs. alternatives. Does not mention any prerequisites, exclusions, or context for use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the agent knows it is a safe read operation. The description adds 'tenant-scoped' and lists entities, but does not disclose what the tool actually returns or any behavioral traits beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise, but it fails to convey substantive information. It uses vague language and does not earn its place with useful content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high parameter count (13) and low schema coverage (15%), the description is incomplete. It does not explain the tool's purpose, output, or how parameters interact, leaving significant gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only 15% of parameters have descriptions in the schema, yet the description provides no explanation of the 13 parameters. It adds no meaning to the input schema, leaving the agent without guidance on which parameters to use or how they relate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses 'Operate on' as the verb, which is vague and does not specify the actual action (e.g., 'list', 'check', 'validate'). The title suggests 'policy check', but the description fails to clarify. It lists multiple entity types without indicating what the tool does with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the many estimator_ sibling tools with specific actions (e.g., add_line, convert_to_bid). The agent lacks context on the intended use case or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe, read-only behavior. The description adds no further behavioral context (e.g., authentication, rate limits) and uses the ambiguous verb 'operate,' which could mislead. No contradiction with annotations, but no added value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, but it is under-specified and fails to convey essential information. Conciseness does not compensate for lack of substance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 parameters, nested objects, output schema, many sibling tools), the description is grossly inadequate. It does not explain what the tool returns, how to use parameters, or when to prefer it over alternatives.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 15%, yet the description provides no parameter-level information. It mentions none of the 13 parameters, leaving the agent without guidance on how to populate them. This is a critical gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The name 'estimator_receipt_get' and title clearly indicate getting a receipt. However, the description uses the vague verb 'operate' without specifying retrieval, and fails to differentiate from sibling estimator tools that also deal with similar entities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description is too generic to help an agent decide under what conditions to invoke this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare safe read and idempotent. Description adds pagination behavior and the 'safe shape' concept, but does not reveal additional behavioral traits beyond what annotations and schema imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states purpose, second provides usage pattern and follow-up action. No redundancy, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With output schema present and annotations covering safety, the description explains pagination and required fields sufficiently. Tool complexity is well-addressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds a usage example but repeats schema info like 'Prefer this over the legacy aid field' without deeper semantics. Minimal added value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Fetch' and the resource 'StackFast Brain search result by id'. It distinguishes from sibling tools by specifying the AI6 MCP reader plane and the safe shape pattern.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage example with id, page, page_size and explains pagination via next_page until complete is true. Does not explicitly state when not to use, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description contradicts the annotation readOnlyHint=true by stating it can 'start' or 'append,' which implies write operations. This is a clear contradiction. The description adds one behavioral note about output state but is overall misleading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise, but it lacks structure and does not efficiently convey necessary information. The sentence is somewhat vague and could be front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool (11 optional parameters, 2 enums, multiple actions), the description is far from complete. It fails to cover the action enum, parameter roles, or output semantics, relying entirely on schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage and the description failing to explain any of the 11 parameters, there is no added semantic value. The description offers no details on how parameters like 'action', 'source', or 'answers' are used.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool starts or appends a GrowthOS Business Brain Interview, referencing a specific model. This gives a clear verb and resource, but does not differentiate from sibling tools like growthos_scorecard, which may have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It lacks any context about prerequisites, when to perform start vs append, or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds context about 'draft' nature and the condition for returning draft_review_required, but does not disclose additional behavioral traits beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences that are front-loaded with the core purpose and inputs, followed by constraints. No extraneous words, every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has nested objects and an output schema, the description adequately covers the input context and conditions. The output structure is not explained, but output schema exists to cover that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description repeats the schema descriptions verbatim without adding new meaning. Baseline 3 is appropriate as no extra value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the verb 'Build', the resource 'draft GrowthOS digital-clone render packet', and the inputs: 'normalized signals, evidence, runtime tenant voice profile, and PERSPECTIVE capability grounding'. It also includes negative constraints ('No Robert voice defaults and no autonomous outbound'), distinguishing it from sibling tools like growthos_business_brain_interview.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states required inputs (tenant_profile, prospect) and a condition ('missing profile returns draft_review_required'). It includes a negative constraint but does not explicitly compare to sibling tools or specify when to use this tool over alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context by describing the use of a 'gate-first policy layer' and stating that no new persistence table is created, which goes beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the main action and key details, with no extraneous words. Every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the nested object parameter and the presence of an output schema, the description adequately covers the tool's function (types, policy layer, persistence). It is complete enough for an agent to understand the tool's role without needing further details about return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the one parameter, and the schema description already specifies the opportunity_type constraint. The tool description adds context about the types of opportunities, but the parameter semantics are largely covered by the schema, resulting in a baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Build') and the resource ('Opportunity Scout packet'), lists the specific types (customer, talent, contract, capital), and references a distinguishing policy layer, differentiating it from sibling tools like growthos_revenue_capture_packet.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for building packets for the listed opportunity types but does not explicitly state when to use this tool versus alternatives (e.g., growthos_revenue_capture_packet, talent_scout_create_packet), nor does it provide when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that the tool does not send autonomously and includes optional composition behavior, providing context beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence of 25 words with no wasted text, conveying the essential action and constraints efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With annotations and output schema present, the description covers the main purpose and behavioral note. However, it omits explanation of 'step 3' referenced in the schema and the report content beyond 'scorecard.'

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (only CogentCast params documented). The tool description does not explain the 'sender' or 'prospect' parameters, failing to add meaning beyond the schema for those critical inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a scorecard into a sendable report with multiple output formats (web, email, PDF) and optional CogentCast composition. It uses specific verbs and resources, and distinguishes from sibling tools like growthos_scorecard.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'No autonomous send,' telling the agent the tool does not send the report. However, it does not provide explicit guidance on when to use versus alternatives or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true; description adds value by stating 'No autonomous outbound' and explaining that the tool may fetch a CogentCast receipt (a read operation). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences that front-load the output and input. No filler, but could be slightly more structured (e.g., bullet points for components). Still well within acceptable bounds.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (4 parameters with nested objects, output schema exists), the description adequately lists output components but does not clarify input mapping, prerequisites, or dependencies. Output schema handles return details, but input guidance is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only 50% of parameters have descriptions in the schema; the tool description does not compensate for undocumented parameters like 'sender' and 'prospect'. It mentions 'supplied local-business evidence' but fails to map this to specific parameters or explain their structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies what the tool does: returns a revenue-capture packet with specific components (scorecard, contact drafts, CogentCast receipt composition, summary) for local-business evidence. It distinguishes from siblings by naming unique output elements and mentioning CogentCast integration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for local-business evidence with optional CogentCast receipt, but lacks explicit when-to-use or when-not-to-use guidance. No comparisons to sibling tools like growthos_opportunity_scout_packet, leaving ambiguity for an AI agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint, idempotentHint, destructiveHint. The description adds that it never sends outreach and builds a private scorecard, reinforcing safety and non-intrusive behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each adding essential information: purpose, access, and output scope. No redundant or irrelevant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With complete schema coverage, annotations, and output schema, the description adequately covers purpose, access, and behavioral boundaries. It could briefly mention optional batch input, but the schema already handles that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description does not need to add parameter details. The description's mention of 'public business signals' is generic and does not conflict with schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool builds a private GrowthOS Revenue Capture Scorecard from public business signals, using specific verb and resource. It also distinguishes by noting it never sends outreach.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions access requirements ('reader entitlement') and that it returns findings only, but does not explicitly tell when to use this tool over alternatives like growthos_opportunity_scout_packet.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states the tool composes a packet with an audit trail, implying side effects, but the annotation declares readOnlyHint=true, which indicates no state modification. This is a direct contradiction between the description and annotations, severely undermining transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence that lists many components, which could be more concise. It is front-loaded with the main purpose but includes a comma-separated list that reduces clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (14 parameters, nested objects, output schema), the description does not explain how to use parameters, what the returned packet contains, or any prerequisites. It is insufficient for an AI agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not explain any of the 14 parameters, and the schema has 0% coverage. The description mentions terms like 'do_not_say' and 'safe_phrasing' but these do not correspond to parameter names, adding no meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool composes a 'relationship-safe correspondence decision packet' and explicitly says it never sends the message, which distinguishes it from any sending tool. The verb 'compose' and resource 'decision packet' are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context that the tool is for composing a packet without sending, hinting at use for drafts requiring review. However, it does not explicitly state when to use this tool versus alternatives or when not to use it, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds that it operates through the AI6 MCP reader plane and returns result ids, which provides useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that front-loads the purpose and includes actionable instruction. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so description need not detail return values. It mentions using fetch with result id, which is helpful. Could mention pagination or result format but not necessary for this simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with description for 'query'. Description adds that it searches StackFast Brain knowledge but does not add syntax or formatting details beyond schema, so baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches StackFast Brain knowledge and differentiates from the sibling 'fetch' tool by instructing to use fetch with returned result id for full text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use fetch for full text after search, providing clear next step. Does not explicitly list when not to use this tool versus other search tools, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true. The description adds that the tool returns metadata/URLs and intentionally omits raw contents, which is consistent and provides additional behavioral insight beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the key action and result, and includes an important intentional omission detail. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 0% parameter coverage and no guidance on how to use the tool (e.g., which parameters are required, how artifacts are identified), the description is incomplete. The presence of an output schema does not compensate for missing parameter semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the description provides no information about the four parameters (limit, filename, session_id, artifact_id). It fails to add any meaning beyond the schema, which is empty of descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's purpose: returning session artifact metadata and persistent URLs. It explicitly states what V1 omits (raw artifact contents), distinguishing it from potential raw content tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies that this tool is for metadata and URLs, not raw contents, but does not explicitly name alternatives or provide when-not-to-use guidance. The context is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description reinforces with 'Draft/review only; no sends or applications,' adding clarity that no actions are performed. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a list of deliverables in a single sentence. It is front-loaded and efficient for the complexity, though lengthy due to the number of items.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high complexity of the tool (many output components), the description covers all essential aspects: what is built, the draft-only nature, and the scope. The presence of an output schema further supports completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 64%, so baseline is 3. The tool description does not add additional meaning to the parameters beyond what the schema already provides. The description focuses on outputs, not parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool builds a detailed workup for a Talent Scout queue item, listing many specific components. It distinguishes from siblings by ending with 'Draft/review only; no sends or applications.' This clearly defines its scope vs. other tools like talent_scout_compose_application.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: it is for drafting/reviewing, not sending. It does not explicitly exclude alternatives or state when not to use it, but the scope is well-defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description adds that the tool verifies before recommending, never sends the email, and requires human approval. This provides useful behavioral context not captured in annotations, though it does not detail what happens on verification failure or the exact nature of the receipt.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the core purpose and key behavioral characteristics. It is front-loaded with the main action and avoids redundant elaboration, making it quick for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 12 parameters and an output schema, the description provides sufficient high-level context (verification, no-send, approval) but lacks detail on how inputs relate to the receipt or what the output contains. It is adequate for a simple tool but not fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 33% schema description coverage, the description adds no value for the 8 undocumented parameters. It does not explain what parameters like domain, first_name, etc., contribute to the enrichment process. The description is too generic to assist the agent in correctly populating inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool prepares business email enrichment receipts for qualified contacts, using Hunter.io-style methodology. It distinguishes from other talent_scout tools (e.g., talent_scout_compose_application) by focusing on email enrichment rather than applications or profiles, but does not explicitly differentiate from all siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool should be used when a business email is needed but requires verification and human approval before acting. It states 'never sends' and 'requires human approval,' but provides no when-not-to-use or alternative tools, leaving usage context somewhat implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: it composes artifacts without sending/applying, uses JD evidence, and never returns raw owner-provided data (e.g., 'never returned raw'). It does not contradict annotations and provides additional non-obvious information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: first defines the core purpose with specific artifact types, second lists explicit exclusions. Every sentence adds value without redundancy, and the structure front-loads the most critical information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 22 parameters and an output schema, the description covers the main purpose, supported output types, and constraints (e.g., 'never returns raw'). It doesn't explain prerequisites like using queue_item_id vs title+company, but the schema descriptions handle that. Overall, it provides sufficient context for an agent to understand the tool's role and boundaries.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 73%, so the schema already documents most parameters. The description adds meaning beyond schema by explaining the output_kind enum variants, noting that certain evidence parameters are 'never returned raw', and clarifying the role of parameters like user_supplied_jd_text as a fallback. This provides useful context that the schema alone does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('compose') and resource ('first-party job-seeker application artifact from a real Talent Scout queue item using JD evidence'). It explicitly lists supported artifact types (cover letter, form paste, etc.) and clearly states what it never does ('sends, applies, screens people, ranks people, or makes hiring decisions'), distinguishing it from sibling tools like talent_scout_record_application.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear boundaries on when to use the tool ('supports cover letter, form paste, application Q&A, telephone script, and authority analysis only') and what not to use it for ('never sends, applies, screens people...'). However, it does not explicitly name alternative sibling tools for the excluded actions, so guidance is slightly implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description says 'Create' indicating a write operation, but annotations declare readOnlyHint=true, which is a direct contradiction. This undermines trust and scores 1 per guidelines.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no fluff. The main action is front-loaded, and every sentence provides useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description misses key context like parameter details and behavioral nuances beyond draft-only and approval. The annotation contradiction further reduces completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only implicitly mentions queue_item_id as 'queue item' but fails to explain the other 5 parameters, adding minimal value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it creates a draft-only packet from an existing queue item, with a specific verb and resource. It distinguishes from siblings by specifying the input (queue item) and the draft-only nature.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: use when you have a queue item and need a draft packet requiring human approval. However, it does not provide explicit when-not-to-use or alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description aligns with annotations (readOnlyHint=true, destructiveHint=false) by stating 'Read-only control-tower view; no sends or applications.' It adds valuable context about server-side mailbox reconciliation via 'StackFast service-account reader' and the constraint not to substitute client-side reads, which goes beyond annotation information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured: it front-loads the main purpose, enumerates components, and then provides critical behavioral constraints. Each sentence adds value, though some trimming could improve readability without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 10 parameters, presence of an output schema, and annotations, the description covers the tool's behavior adequately. It explains the output components and important constraints (mailbox reconciliation). Minor omission: no mention of how sibling tools differ, but overall complete for an experienced agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 60%, the description adds contextual meaning for some parameters (e.g., 'bounded needs_role_hydration recovery' relates to hydration_limit), but it does not cover the 4 undocumented parameters (tenant_id, slate_limit, section_limit, etc.) in the main text. The description's overall richness partially compensates for these gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool returns 'the closed-loop Talent Scout daily operating report from the shared tenant queue' and lists many specific data components (applied pipeline, mailbox reconciliation status, etc.), clearly distinguishing it from sibling tools like talent_scout_pipeline_describe which likely provides a simpler pipeline view.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear guidance: 'Clients MUST NOT invoke their own Gmail/email connector' and specifies the action to take if mailbox_reconciliation_status is not ok. It implies a read-only control-tower view. However, it does not explicitly contrast with alternative sibling tools like talent_scout_review_queue or talent_scout_pipeline_describe, missing an opportunity for stronger when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that the tool 'never scrapes LinkedIn' and reinforces read-only default, providing behavioral context beyond annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, single paragraph of three sentences, front-loading the main purpose. Every sentence adds value, with no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with good annotations and an output schema, the description explains the output (websites, confidence, receipts, next actions), default behavior, and restrictions (no LinkedIn scraping). Adequate for agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 58% with 7 of 12 parameters having descriptions. The tool description does not elaborate on parameters beyond what the schema provides, so it adds minimal value. Baseline 3 is appropriate given coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool previews the account owner's saved business-list campaign and returns specific data (company websites, employee-count confidence, source receipts, next actions). The name and context differentiate from similar siblings like talent_scout_discover_local_companies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains that the tool is read-only by default and does not persist unless explicitly set, and never scrapes LinkedIn. This provides clear guidance on when to use (preview) and when not to (if persistence or LinkedIn scraping is needed), though alternatives are not explicitly named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond annotations by specifying return data (public websites only, confidence, receipts) and default read-only behavior. No contradictions with annotations (readOnlyHint=true, etc.) were found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (two sentences, 45 words), front-loaded with the tool's core purpose and key behavioral notes. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite an output schema existing, the description does not cover many aspects of the complex tool (18 parameters, low schema coverage). Missing details on refresh logic, geography, target lanes, etc., leaving significant gaps for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (39%), yet the description only briefly mentions `persist_results`. It fails to compensate for the undocumented parameters, leaving many parameters without semantic context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Preview' and the resource 'saved local business-list campaign', and distinguishes from siblings like talent_scout_discover_companies_by_campaign by specifying 'local' and 'campaign'. It also outlines the return values (public company websites with size-band confidence and source receipts).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use the tool as a read-only preview, with explicit guidance on the `persist_results` flag. However, it does not explicitly contrast with sibling tools or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.