Meta Council

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

Description discloses destructive nature ('approve or reject') and requires authentication. Aligns with annotations (destructiveHint=true, readOnlyHint=false). Adds value beyond annotations by specifying authentication need.

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 with no wasted words. Front-loads action, then prerequisite and requirement. Highly 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 output schema exists and annotations are present, description covers purpose, usage, authentication, and behavioral traits. No gaps identified.

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 is 3. Description adds context for session_id (referencing source tools) and action (approve/reject), but no additional meaning 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?

Description clearly states the verb 'Advance' and resource 'workflow past a human checkpoint', specifies actions 'approve or reject', and distinguishes from siblings by referencing session id from run_workflow/get_workflow_session.

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 states when to use (after human checkpoint) and prerequisites (session id from related tools), but does not mention when not to use. The context is clear enough.

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. Description adds only 'Requires authentication', which is minimal extra context. 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?

Single concise sentence with essential details, plus a separate authentication note. No superfluous 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?

Lists all key metrics (pipeline stages, reply rate, per-stage counts). Output schema exists, so return value explanation is unnecessary. Complete for a simple stats retrieval 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 coverage is 100% with campaign_id described as 'Campaign UUID (from list_outreach_campaigns).' Description adds no further semantic detail beyond referencing 'one outreach campaign.'

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 verb ('Pipeline-stage breakdown'), resource ('one outreach campaign'), and specific metrics ('total / sent / active / won / lost, reply rate, per-stage lead counts'). Distinguishes from sibling tools like outreach_analytics and list_outreach_campaigns.

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?

Implicitly suggests use for detailed campaign breakdown, but no explicit when/not-to-use guidance or mention of alternatives. Sibling tool context provides some differentiation, but description doesn't leverage 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds value by specifying the exact fields returned (role, description, default model, etc.), which is behavioral context beyond annotations. 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 single, well-structured sentence that front-loads the main action and lists key output fields. No extraneous information; 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?

With an output schema present, the description need not detail return values, yet it still lists key fields. The tool is simple (one parameter) and the description covers purpose, usage context, and output, making it fully complete for an 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?

Schema coverage is 100% with the slug parameter already described. The description adds minor context ('from list_agents') but does not significantly enhance parameter meaning beyond the schema. Baseline 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 the tool retrieves full detail for one agent by slug, listing specific fields (role, description, etc.). It distinguishes from the sibling list_agents by focusing on a single agent with comprehensive info.

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 mentions 'from list_agents' implying that list_agents should be used first to obtain slugs. This provides clear context on when to use this tool versus list_agents, though it does not explicitly 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.

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

Annotations indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is clear. Description adds value by specifying the return content ('full results including all agent opinions and the synthesis'), providing context beyond annotations. 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?

Description is a single sentence (16 words) that front-loads the purpose and includes essential details. No redundant or extra 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 an output schema (not shown but present), annotations covering safety, and a single well-documented parameter, the description is complete enough for the agent to understand what the tool does and when to use it.

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% with a single parameter `session_id` described as 'The session ID to retrieve'. The description does not add additional semantics beyond what the schema already provides, so baseline score 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?

Description clearly states 'Get the full results of a previous Meta Council session' with specific verb 'get', resource 'full results of a previous Meta Council session', and details about content ('all agent opinions and the synthesis'). This distinguishes it from sibling tools like `get_workflow_session` or `run_council`.

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 (retrieve results given a session_id) but does not explicitly state when to use this tool vs alternatives like `get_workflow_session` or `run_council`. No when-not or exclusion guidance 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 indicate read-only, idempotent, non-destructive behavior. The description adds important context: it returns booleans for API keys, never secret values, and requires authentication. This extends 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 core purpose and specific details, with no unnecessary 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?

For a zero-parameter tool with an output schema, the description fully covers: what is returned (specific fields), what is not (secret values), and the requirement (authentication). It leaves no ambiguity.

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 baseline is 4. The description adds no parameter info but compensates by clarifying the return contents, which is helpful given zero-param tools often need output 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 uses a specific verb ('Get') and resource ('settings'), listing exact data elements (preferred model, plan tier, API key booleans). It clearly distinguishes from sibling tools which are action-oriented or retrieve different resources.

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 a prerequisite ('requires authentication') but does not provide guidance on when to use this tool over its many siblings, nor does it mention alternatives 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 already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, indicating safe, non-mutating behavior. The description adds critical context: return content (machine-readable spec + SVG URL or raw SVG), the effect of include_svg, and authentication/tenant boundary enforcement. 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?

Three concise sentences. First sentence states purpose and output, second clarifies source of artifact IDs, third covers authentication. Every sentence adds information with no redundancy. Front-loads the main action and result.

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 low complexity (2 parameters, existing output schema), the description fully covers what an agent needs: what it does, what it returns, where to find IDs, and authentication requirements. No gaps remain.

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% with clear parameter descriptions. The description adds value by linking parameters to output behavior: 'Returns the machine-readable spec... or the raw SVG itself with include_svg=true.' This contextualizes the boolean parameter effectively, going beyond the schema's static 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 tool fetches a chart artifact from council/LOCUS sessions, specifying 'Fetch a chart artifact generated by a council session or LOCUS determination.' This distinguishes it from all sibling tools, which deal with campaigns, workflows, or agents.

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 where artifact IDs come from ('Artifact ids appear in session results as 'visualizations' / 'visualization' reference blocks'), giving clear usage context. It does not explicitly state when not to use it, but no sibling tool serves the same purpose, so this is acceptable.

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 and idempotentHint, making safety clear. Description adds behavioral context about polling (useful for timeouts) and requires authentication, adding value 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 sentences, front-loaded with main purpose, no filler. 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?

Includes authentication requirement, usage context, and output schema exists (even if not shown). Complete for a polling tool with good 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?

Schema coverage is 100% with one well-documented parameter. Description does not add extra meaning beyond the schema, meeting baseline expectations.

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 polls a workflow session for step-by-step status and output, with specific context about when it's useful (timeout or checkpoint). It distinguishes from siblings like run_workflow.

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 context for when to use (timed out, awaiting checkpoint) and mentions authentication requirement. Does not explicitly exclude other scenarios or name alternative 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 and idempotentHint=true, so the description adds marginal context about the return fields. It does not disclose behaviors like pagination or limits, but with good annotation coverage, a 3 is appropriate.

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 conveys the tool's purpose and output. Every word adds value, with no redundancy or unnecessary details.

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 simple list tool with one optional filter, the description provides sufficient context alongside annotations and an output schema. It could mention default behavior when no domain is specified, but overall it is adequately 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?

The input schema has 100% description coverage with a clear explanation of the domain parameter. The tool description adds no additional meaning about the parameter beyond what the schema provides, so baseline 3 applies.

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 all available expert agents and specifies the information returned (roles, domains, specialties). It uses a specific verb ('List') and resource ('expert agents'), distinguishing it from sibling tools like get_agent_detail.

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 does not explicitly state when to use this tool versus alternatives like get_agent_detail. Usage context is implied but no direct guidance on exclusions or alternative scenarios is 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's a safe, idempotent read. The description adds that results are newest first and include specific fields, but doesn't mention pagination behavior (limit, max) or default direction. With strong annotations, the description adds moderate 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?

A single, front-loaded sentence that efficiently conveys the action, resource, ordering, and key output fields. No wasted 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 presence of an output schema and rich annotations, the description is adequate but minimal. It doesn't mention that campaign_id is required (though schema does), nor does it summarize default behavior for limit and direction. For a list tool with sibling tools, it could provide more context but is not severely lacking.

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 schema already documents all three parameters. The description does not add any additional meaning or context about parameters (e.g., format, constraints, relationships). 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 lists emails for an outreach campaign with specific details (newest first, subject, body preview, reply classification). This distinguishes it from siblings like list_outreach_campaigns (which lists campaigns) and helps an agent immediately understand the tool's purpose.

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 (e.g., search_outreach_leads, outreach_analytics). It only states authentication requirement, which is obvious. There's no when-not or context about filtering or prerequisites beyond the schema.

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, so the safety profile is covered. The description adds that it lists triggers and requires authentication, which provides context but does not significantly extend behavioral 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?

The description is a single, front-loaded sentence that covers the purpose without any extra words. Every part 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?

Given the presence of an output schema, the description does not need to detail return values. It explains what triggers are included. It is complete for a list tool, though it omits potential pagination details.

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 campaign_id parameter's description ('Campaign UUID (from list_outreach_campaigns)') adds a useful source reference that the schema alone (just 'string') does not provide. This helps the agent understand dependencies.

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 'List' and the resource 'automation triggers' with specific examples (auto-reply rules, status updates, notifications). It is well-differentiated from sibling tools like list_campaign_replies (replies) and list_outreach_campaigns (campaigns).

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 (for an outreach campaign) and mentions authentication, but lacks explicit guidance on when to use versus alternatives or when not to use. However, the context is clear enough for an agent to infer appropriate usage.

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 (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already indicate a safe read operation. The description adds value by specifying the output includes 'live lead / sent / reply counts' and that authentication is required, going 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, clear sentence that is front-loaded with the main action. While very concise, it could benefit from a slightly more structured format (e.g., listing key features), but there is no wasted text.

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 simplicity (no parameters, likely a straightforward listing) and the presence of an output schema (though not shown), the description fully covers what the tool does, for whom, and what the output includes. No additional context is necessary.

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 0 parameters with 100% coverage, so the baseline is 4. No parameter information is needed, and the description does not add any parameter semantics because there are none.

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 lists the authenticated user's outreach campaigns and includes specific return data (live lead, sent, reply counts). It uses a specific verb and resource, distinguishing it from sibling tools like list_campaign_replies or search_outreach_leads.

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 'Requires authentication' but provides no guidance on when to use this tool versus alternatives like list_campaign_replies or campaign_pipeline_stats. Usage context is implied but not explicitly stated, and no exclusions or when-not scenarios are given.

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, so the safety profile is clear. The description adds that the tool returns descriptions and agent counts, but does not disclose other potential behavioral traits (e.g., pagination, ordering, filtering). The added value over annotations is modest, earning a baseline 3.

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-formed sentence that conveys all key information without redundancy. It is appropriately front-loaded and concise.

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 simplicity (no parameters, clear output schema), the description is complete. It covers the purpose and the nature of the output, and the output schema handles return value documentation. No further context is needed.

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 zero parameters, so baseline 4 applies. The description adds no parameter information because none exist. No improvement needed.

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 lists all available expert panels with descriptions and agent counts. It clearly identifies the resource ('expert panels') and the output fields, but does not explicitly differentiate from sibling tools like 'recommend_panel'. However, the verb 'list' distinguishes it from recommendation 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 provides no guidance on when to use this tool versus alternatives such as 'recommend_panel' or 'list_agents'. There is no indication of prerequisites, context, or conditions 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 indicate readOnlyHint=true and idempotentHint=true, describing a safe, idempotent list operation. The description adds value by detailing the return fields and the nature of pipelines (multi-step, composable), which is 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, front-loaded sentence with no wasted words. Efficiently conveys purpose and return 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?

For a zero-parameter, read-only list tool with output schema, the description is complete. It explains what is listed and what is returned, with annotations covering safety. No gaps.

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 baseline is 4. Description adds no parameter info but doesn't need to. Schema coverage is 100%, so no 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 description clearly states the tool lists available multi-step workflow pipelines with specific fields (slug, description, per-step model). It distinguishes from sibling tools like advance_workflow and run_workflow by specifying it's for listing composable bundles.

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 viewing available workflows and what each returns, but lacks explicit when-to-use or alternatives compared to siblings like run_workflow or get_workflow_session. Still, the purpose is clear enough for an agent to decide.

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, and destructiveHint=false, showing the tool is safe and idempotent. The description adds valuable behavioral context: 'Deterministic — no LLM, instant' and explains the application of override floors, which aligns with and enhances 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 moderately concise, with a clear front-loaded statement of purpose and a structured explanation of inputs and behavior. It is slightly longer than necessary but every sentence adds value, earning a solid 4.

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 (8 parameters, nested objects, output schema exists), the description thoroughly explains the algorithm, input formats, authentication requirements, and key behavioral traits. It provides complete context for an agent to correctly invoke the 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 coverage is 100%, with each parameter already having a description. The description adds context about the two input modes being mutually exclusive and explains the shape of agent_scores, but this adds only moderate value beyond the schema. Baseline 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 the tool computes a LOCUS Level of Care from dimension ratings, emphasizing determinism, instant computation, and the use of composite scores, Determination Grid, and override floors. It distinguishes itself from sibling tools like 'score_locus_case' by focusing on determining the level from already-existing scores.

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 to provide either flat D* ratings or a per-reviewer agent_scores map, clarifying two mutually exclusive input options. It implies usage when scores are already available, but does not explicitly mention when to avoid using the tool or provide alternative tools, limiting full usage 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, idempotentHint, and destructiveHint, so the safety profile is clear. Description adds the authentication requirement, which is helpful behavioral context. No additional traits (e.g., data freshness, rate limits) are disclosed.

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 wasted words. Information is front-loaded, stating the purpose and then the authentication requirement.

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 simple read-only tool with zero parameters and an available output schema, the description provides sufficient context. It could be slightly improved by specifying that it pertains to the authenticated user, but overall it is adequate.

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?

Tool has no parameters (0 params, 100% schema coverage). Baseline for 0 params is 4. Description does not need to add parameter info, and it correctly omits any.

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 the tool provides an outreach summary with specific metrics (total leads, sent, replied, reply rate). It uses specific verbs and resources, and distinguishes itself from sibling tools that focus on campaigns or individual lead searches.

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. Does not mention scenarios where it is appropriate or inappropriate, nor does it reference sibling 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 declare readOnlyHint and idempotentHint true, and destructiveHint false. The description adds valuable context: authentication is required because the query may be sent to an embedding provider, and the matching algorithm uses semantic match with fallback. This goes 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 sentences convey purpose, method, output, integration, and authentication. Every sentence is informative and necessary. 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 single-parameter tool with an output schema and comprehensive annotations, the description covers purpose, algorithm, integration target, and security context. It is fully adequate for an AI agent to understand and invoke 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 coverage is 100% for the single parameter 'query', so baseline is 3. The description adds high-level algorithmic context but does not provide additional detail about the parameter beyond what the schema already describes.

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 recommends an expert panel using semantic match with keyword fallback. It distinguishes from siblings by explicitly linking the output to run_council's panel argument, making it clear what unique purpose this tool serves.

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 to feed the result into run_council's panel argument and mentions authentication requirements. It does not explicitly state when not to use it, but the sibling context and specificity are 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?

The description discloses that the process starts asynchronously by default, returns a session ID, and includes independent analysis with synthesis and transparency. This adds significant behavioral context beyond the annotations (readOnlyHint=false, destructiveHint=false) by clarifying the async nature and result retrieval method.

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 consists of two well-structured sentences: the first explains the purpose and process, the second provides actionable guidance on async behavior and follow-up. Every word contributes 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?

Given the tool has 4 parameters, an output schema for return values, and annotations, the description adequately covers the workflow (async, panel analysis, synthesis, session ID). It is sufficiently complete for an agent to understand invocation and follow-up, though edge cases or failure modes are not 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?

With 100% schema description coverage, the schema already documents all parameters comprehensively. The tool description does not add additional semantic details or examples beyond what is already in the schema, so it meets the baseline but does not exceed it.

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 that the tool submits a question or decision to Meta Council for analysis by a panel of AI agents and synthesis into a recommendation. This specific verb-resource combination distinguishes it from sibling tools like run_workflow or get_session.

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 asynchronous start and directs to use get_session with the session ID, providing some follow-up guidance. However, it does not explicitly state when to use this tool versus alternatives like recommend_panel or run_workflow, nor does it provide exclusions or prerequisites.

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?

Discloses that it starts a pipeline (mutation), uses user keys, handles human checkpoints, and requires auth. Adds value beyond annotations (readOnlyHint=false, openWorldHint=true, etc.) 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?

Four sentences with front-loaded main purpose and no redundant information. 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?

Covers core behavior, async/sync modes, provider keys, human checkpoints, and auth. Given the presence of an output schema, return value details are not needed.

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%. The description adds context: query specificity, workflow slug source with examples, wait_seconds effect on sync waiting, complementing schema definitions.

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 (start), resource (workflow pipeline), and key behavior (returns session id, default async). It distinguishes from siblings like advance_workflow and get_workflow_session.

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?

Explains provider key usage, human checkpoints, and authentication. While it does not explicitly contrast with alternatives, the context implies when to start vs. poll/advance.

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 discloses key behaviors beyond annotations: convenes a panel, deterministic aggregation, inviolable safety floors implemented in code, async start by default, and audit trail return. No contradictions with annotations (readOnlyHint=false, etc.).

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 paragraph with clear topic sentences and each sentence adds value. It could be more concise by omitting some procedural details (e.g., panel composition), but it remains well-structured and focused.

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 (multiple steps, panel, safety floors), the description covers essential aspects: adult-only constraint, anonymization requirement, async behavior, output (Level of Care + audit trail). The presence of an output schema makes the lack of return value details acceptable.

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% (all parameters documented). The description adds minimal extra meaning beyond the schema: 'case' is clinical text, 'model' is optional override, 'wait_seconds' relates to sync/async behavior. While it contextualizes parameters, the semantic value added is marginal.

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 purpose: scoring anonymized adult mental-health/addiction cases against LOCUS. It specifies the process (panel aggregation, deterministic engine, safety floors) and distinguishes from siblings like 'locus_determine_from_scores' which handles a different step.

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 states constraints: adults only (not children/adolescents), must use anonymized cases, requires authentication, and starts asynchronously (poll get_session). However, it does not explicitly contrast with sibling tools like 'locus_determine_from_scores' or when each is appropriate.

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, idempotentHint, destructiveHint. The description adds the authentication requirement and specifics about returned fields (company, contact, etc.), which are useful beyond the annotations. 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, each earning its place. First sentence describes action and filters; second adds return info and auth requirement. No redundant words, front-loaded with key 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?

With an output schema present, the description appropriately highlights key return fields. It covers purpose, filters, output summary, and auth. Annotations handle safety, so no gaps remain.

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 is 3. The description summarizes parameters (text query, status, campaign) but does not add new semantic details beyond the schema's descriptions. No examples or formatting hints.

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 'Search the user's outreach leads' with specific verb and resource. It lists filters (text query, pipeline status, campaign) and return fields (company, contact, status, pitch, reply info). This distinguishes it from sibling tools like list_outreach_campaigns which focus on campaigns.

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 usage context: filtering leads by multiple criteria. It explicitly requires authentication. However, it does not provide explicit when-not-to-use guidance or alternatives to other tools, though the sibling list suggests distinct purposes.

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