COS Monitor

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that analysis runs in parallel across 4 frameworks and lists the output categories (scores, dimension breakdowns, recommendations, cross-framework insights). This adds meaningful context beyond the schema, though it does not explicitly state side-effect-free behavior; analysis is inherently read-only, so the risk is low.

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 at 5 lines, uses a clear bulleted list for outputs, and front-loads the core function. Every sentence adds value: the parallel execution fact and the output summary are non-redundant. No fluff or repetition exists.

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 provides a helpful high-level summary of return structure, covering overall scores, dimension breakdowns, recommendations, and cross-framework insights. It also highlights the parallel execution aspect. It does not mention parameter-specific effects (e.g., platform affects scoring weights), but those are in the schema. The description is sufficiently complete for an agent to understand what the tool does and what it returns.

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 each parameter is already documented in the schema. The description does not add any extra meaning about the parameters—it does not mention platform or target_audience, leaving their roles entirely to the schema. This matches the baseline where the schema does the heavy lifting.

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 verb ('Analyze'), resource ('content'), and scope ('all 4 COS frameworks in parallel'). This clearly distinguishes it from sibling tools like analyze_framework, which likely target a single framework. The purpose is unambiguous and differentiates from alternatives.

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 clearly implies this is the comprehensive analysis tool ('using all 4 COS frameworks in parallel'), providing clear context that alternatives like analyze_framework are narrower. However, it does not explicitly state when not to use this tool or point to specific siblings, so it lacks overt exclusions or alternative routing.

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?

With no annotations available, the description carries the burden of behavioral disclosure. It adds useful behavior beyond the schema by explaining that the tool restricts to one framework, is faster than full analysis, and specifies what each framework evaluates. It does not discuss side effects or auth, but this is a non-destructive analytical tool and the performance/scope disclosure is meaningful.

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 short, front-loaded with the core purpose, and uses a bulleted list for framework details. Every sentence earns its place with no filler or repetition of schema 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 output schema exists and parameters are fully documented, the description covers the essential decision-making information: what the tool does, when to use it, and the framework options. It is slightly light on explicit routing to alternative siblings, but the 'full analysis' contrast provides enough context for correct 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds real value by explaining each framework enum value in behavioral terms (e.g., 'hape: Engagement Analysis (novelty, relevance, emotional valence)'). This goes beyond the bare enum labels in 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 opens with a specific verb and resource: 'Analyze content using a single specific framework.' It immediately distinguishes itself from the broader analysis siblings by emphasizing the single-framework scope and provides a concrete list of framework options, so an agent can tell this apart from analyze_content or analyze_full_comms.

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 a clear usage condition: 'Faster than full analysis when you only need one perspective.' This implies when to prefer this tool over a full multi-framework analysis, though it does not explicitly name the alternative tool 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.

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the tool runs frameworks 'in parallel' and warns that it 'takes longer,' which is meaningful behavioral context beyond a generic 'analyzes content.' For a non-destructive analysis tool, this level of transparency is adequate, though it does not mention potential side effects like content storage or rate limits.

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 well-structured and front-loaded, with a clear verb-first opening, a bulleted list of frameworks, and a direct usage sentence. It is slightly redundant—'most thorough' and 'most comprehensive view' say the same thing—but every sentence otherwise 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 complex tool that runs seven frameworks, the description adequately covers the scope, framework list, usage context, and performance trade-off. An output schema exists, so return-value documentation is not the description's burden. It does not explicitly reference sibling specialized tools, but the sibling list and framework names provide enough context for an agent to choose appropriately.

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 baseline is 3. The description adds only marginal value by noting that Persuasion is 'domain-specific' and listing Platform and Quality as frameworks, which loosely maps to the domain and platform parameters but does not explain them beyond what the schema already states. No additional semantic guidance is 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 clearly states a specific action ('Run all 7 COS frameworks in parallel') and identifies the exact resource and scope. It differentiates from sibling tools by explicitly positioning itself as 'the most thorough analysis option' and listing the included Core 4 and Extended 3 frameworks, which directly maps to the specialized sibling 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 says when to use this tool: 'Use this when you need complete analysis across all dimensions.' It also provides a clear trade-off by noting it 'takes longer but provides the most comprehensive view.' It does not explicitly name sibling alternatives or state when not to use it, so it falls short of a 5.

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 are absent, so the description carries the full burden. It doesn't disclose any behavioral traits such as whether it's read-only, any rate limits, or what the output looks like. It only lists analysis dimensions, which is content, not 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?

Concise and well-structured, with a clear intro and bullet list. The critical domain note is highlighted. No 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?

With an output schema present, the return format is covered. However, the description lacks usage guidance and behavioral transparency, which are important for a tool with many siblings. It's not fully complete but adequate for a straightforward analysis 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?

The schema covers all parameters, but the description adds domain-specific semantics by listing what each domain analyzes, which helps the agent select the right domain. It doesn't add info for other parameters, but since schema coverage is 100%, the baseline is 3; the added domain detail raises it to 4.

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?

States a specific verb ('Analyze'), resource ('content'), and a specific focus ('persuasion frameworks'). The domain list adds specificity. However, it doesn't explicitly differentiate from sibling analyze_* tools, so it's clear but not fully distinguishing.

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 like analyze_content or analyze_quality. It doesn't mention any exclusions or conditions. The agent would have to infer from the name and description.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the analysis categories but does not describe the output format, any side effects, or limitations. Since this is a non-destructive analysis tool, the omission is less critical, but the description still lacks explicit details about what the tool returns or how it behaves beyond the listed evaluation areas.

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 and front-loaded, opening with a clear one-sentence purpose, followed by a focused bullet list of analysis areas. Every sentence earns its place, with no redundant or filler 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 an analysis tool with 3 parameters, one enum, and an output schema present, the description covers the core functionality and supported platforms. It does not detail the return format, but the existence of an output schema likely handles that. The description is complete enough for an agent to understand what the tool does and when to invoke it, though it could optionally mention any preconditions beyond the schema's min length.

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 provides 100% description coverage for all parameters, so the baseline is 3. The description adds no extra meaning about the parameters themselves; it only lists the analysis dimensions (e.g., character limits, algorithm signals) which indirectly relate to the 'platform' parameter but do not deepen understanding of 'content' or 'target_audience' beyond what the schema already states.

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 verb ('Analyze') and resource ('content for platform-specific optimization'), and clearly distinguishes itself from generic analysis tools like analyze_content by focusing on platform constraints and algorithm preferences. The bullet points further specify the exact evaluation areas, making the tool's purpose unmistakable.

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 platform-specific optimization but does not explicitly state when to use this tool versus siblings like analyze_content or analyze_persuasion. No exclusions or alternative conditions are mentioned; the guidance is inferred from the purpose rather than directly stated.

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?

No annotations are provided, so the description carries the full burden. It does disclose the dimensions evaluated, which gives some insight into the tool's behavior. However, it doesn't state whether this is a read-only analysis, any side effects, or limitations beyond the min length specified in the schema. It's adequate but not thorough.

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 and front-loaded: 'Analyze content quality across 5 dimensions' immediately states the purpose, followed by a structured list of dimensions. No wasted words or redundant 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 an output schema present and full parameter documentation, the description provides enough for an agent to understand the tool's function and inputs. It doesn't explain return values, but the output schema covers that. The missing usage guidance is a separate dimension, so overall completeness is high.

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 the description doesn't need to add parameter details. The description doesn't mention parameters, but the schema fully documents content, platform, and target_audience, so the 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 analyzes content quality across five specific dimensions (Clarity, Coherence, Correctness, Completeness, Conciseness). This is a specific verb+resource combination that distinguishes it from siblings like analyze_persuasion or analyze_platform, which focus on different aspects.

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 its siblings. It doesn't mention alternatives or conditions, leaving the agent to infer based on the name and dimensions. For a tool with many siblings, explicit routing is missing.

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?

With zero annotations, the description carries the full behavioral burden inclusively. It transparently reveals the output categories (OCEAN scores, ELM route, vulnerability flags, persuasion principle) and frames the action as an inference/mapping, implying a non-destructive read operation. It omits only minor details like processing limitations or error conditions.

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 primary purpose is stated in the first sentence, and the rest is organized into an action followed by a concise list of return fields. The common-use sentence adds context 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?

The description provides a clear purpose, the main inputs, the expected output fields, and a representative use case, all complemented by a 100%-covered input schema and an output schema. Missing only explicit failure/boundary conditions, which are secondary.

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 all three parameters are already well-described in the input schema. The description adds a practical usage hint (CRM Person/Account description) but doesn't meaningfully expand on any parameter beyond what the schema provides.

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 first sentence uses a specific verb ('infer') and object ('OCEAN personality profile') and immediately distinguishes the tool from generic analysis by stating it maps a free-text audience description into a structured psychological profile. This is clearly distinct from the sibling analysis 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?

Provides clear context: applicable to personalized outreach, ad campaigns, sales messaging, and profiling CRM Person/Account data. However, it does not explicitly state when not to use this tool or compare it to potential 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses the conversational nature and what the agent can help with, but doesn't reveal that the tool is stateful (implied by conversation_id param), whether it can invoke sibling tools internally, or what the response format looks like. Some transparency but meaningful gaps remain for a conversational tool with no annotation coverage.

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 efficiently structured: a one-line purpose statement followed by a four-item bulleted capability list. It's front-loaded with the core purpose and each bullet adds distinct information. No wasted sentences, though the bullet list could arguably be trimmed without losing meaning.

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 that an output schema exists and both parameters are fully documented in the schema, the description covers the main decision-relevant aspects: what the tool does and what kinds of interactions it supports. For a conversational tool, this is reasonably complete, though it could mention that the agent can call underlying analysis tools or note any token/request limits.

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 both parameters (message and conversation_id) already described in the schema itself. The description adds context about what the conversation is for but provides no additional parameter-level detail beyond what the schema offers. Baseline 3 is appropriate when the schema carries the documentation weight.

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: having a conversation with the COS analysis agent. It lists specific capabilities (analyze content, recommendations, framework scores, settings). However, it doesn't explicitly differentiate itself from sibling tools like analyze_content or analyze_framework, leaving the agent to infer that chat is a conversational wrapper vs. direct analysis calls.

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 bulleted list implies when to use the tool (interactive analysis, recommendations, understanding scores, configuring settings), but there's no explicit guidance on when NOT to use it or when to prefer a direct sibling like analyze_content instead. Usage context is implied rather than stated, leaving the agent to guess whether to call chat or the specific analysis 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says 'execute' but does not indicate whether the operation is read-only, has side effects, requires authentication, or is rate-limited. There is no mention of error conditions or consequences of invalid variables. This is a significant gap for a tool that likely performs an analysis run.

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 followed by a practical prerequisite. Every sentence serves a purpose, with no fluff. It is concise and well-structured.

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 tool has an output schema, so return values are covered. The description references get_templates, which is essential for correct usage. However, it does not explain what happens if variables are missing or mismatched, nor does it mention the platform parameter. Given the output schema and the prerequisite, it is adequate but could be more explicit about validation requirements.

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 adds marginal value beyond the schema. It does clarify that variables are template-defined ('required variables' from get_templates), which helps the agent understand the dynamic nature of the variables parameter. Platform is not mentioned, but the schema describes it. 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 states the verb 'execute' and the resource 'template', and clarifies that variables are supplied. It implies a workflow with get_templates, but does not explicitly differentiate from get_template_details. Still, the purpose is specific and distinct from listing templates.

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 a clear prerequisite: 'First use get_templates to find available templates and their required variables.' This tells the agent to retrieve templates first, but does not mention when not to use this tool or alternatives like get_template_details. It provides context but lacks explicit 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?

With no annotations, the description carries the behavioral burden. It explicitly signals a read-only lookup by using 'Get' and 'Returns', and it discloses the categories of information the caller will receive. It does not mention error behavior for invalid template IDs or authorization requirements, but for a pure getter this is reasonably transparent.

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 compact and front-loaded with the core purpose, followed by a scannable bullet list of return contents. Every sentence and bullet 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?

This is a low-complexity tool with one required parameter, a fully documented schema, and an output schema. The description sufficiently conveys what the tool does and what details it returns, so an agent has enough 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 100%; the template_id parameter is already documented in the schema as 'The template ID to get details for.' The description adds no additional meaning beyond the schema, so the 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?

The description uses a specific verb and resource ('Get detailed information about a specific template') and enumerates concrete returned details: variables, categories, tags, and scoring dimensions. It clearly differentiates itself from siblings like get_templates (listing) and execute_template (execution) by emphasizing a single template's metadata.

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 phrase 'specific template' implies this is a point-lookup tool for template metadata, which gives useful context for selecting it over get_templates or execute_template. However, it does not explicitly state when to use it, when not to use it, or name 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?

With no annotations, the description carries the burden, and it does establish that this is a non-mutating list operation and clarifies what a template is. It does not disclose behavior such as whether filtering is applied by default, any pagination, or that it does not run/execute a template.

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 purpose is front-loaded in the first sentence, and the bulleted use-case examples are compact and relevant. There is no redundancy or filler.

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 a simple list operation with no required parameters, fully documented parameters, and an output schema present, the description supplies enough domain context to select the tool. Minor gaps around sibling routing and behavior details are covered by the other dimensions.

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 both search and category are already documented in the schema. The description adds domain context about template use cases but does not elaborate on parameter 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 identifies the action ('List') and resource ('available analysis templates'), and the follow-up definition of templates distinguishes it from direct-analysis tools like analyze_content. However, it does not explicitly differentiate listing from the sibling get_template_details or the executing sibling execute_template.

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 given about when to call get_templates versus alternatives such as get_template_details or execute_template. The description states what the tool returns but provides no conditions, exclusions, or routing cues.

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?

With no annotations provided, the description carries the full behavioral burden. It discloses the composite pipeline, the conditional generate-vs-refine path, optional agent profiling from writing samples, and the full return payload including 'draft_was_generated,' scoring breakdowns, rewrites, and one_thing. It does not mention the default scoring-skip/latency behavior in the description itself, which is left to the include_scoring schema.

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 one-sentence purpose is front-loaded, and the Returns block is organized and scannable. The composite-tool explanation is valuable for a tool this complex, though the bullet list is long enough that some redundancy with the output schema and parameter descriptions exists.

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 composite tool with no annotations, the description covers the main input-to-output flow, the generate-vs-refine conditional, and the intended CRM context, and it lists the key return fields. The main gaps are the purpose of name/title/company/industry and the default scoring behavior, though the input schema and output schema partially fill those 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?

Schema description coverage is 67%, so the description must add some meaning, and it does. It ties audience_description to OCEAN/ELM/Cialdini profiling, writing_samples to agent profiling, and the absence of a draft to automatic generation. The name/title/company/industry parameters remain implicit, but their role is inferable from the CRM-prospect framing.

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 opens with a specific verb phrase and resource: 'Generate or refine a personalized cold email for a CRM prospect.' It then distinguishes itself from the sibling analyzer tools by explicitly labeling itself a composite tool that combines audience profiling, agent profiling, draft generation, and persuasion/platform scoring in a single call.

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 clearly states the intended context: 'Designed for CRM integrations like Clarify, HubSpot, Salesforce — pass a Person/Account context, get back a draft + scoring.' It also implies when to use it over the component siblings by calling itself a composite tool. It does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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?

With no annotations, the description carries full burden. It states the tool 'analyzes' samples, clearly implying a non-mutating read operation. It does not explicitly say 'read-only' or describe side effects, but the analysis-oriented language conveys behavior adequately for this type of tool.

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 efficient and well-structured: the first sentence states the core purpose, the second adds detail, and the third provides a useful contrast. Every sentence adds value with no 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?

The tool is simple with two parameters and an output schema. The description covers the core purpose, input requirements, and what it infers. It does not mention edge cases or prerequisites, but the schema handles parameter constraints, making this sufficient for an agent to call 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?

The input schema already provides descriptions for both parameters (samples and agent_name), achieving 100% coverage. The description repeats the 3-5 sample recommendation and adds context about the inference purpose, but adds little beyond the schema's existing detail.

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 profiles an agent's personality from writing samples, listing specific outputs (Big Five traits, communication style, strengths, blind spots, persuasion profile). It explicitly contrasts with content analysis, making it distinct from siblings like analyze_content and analyze_persuasion.

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 frames the tool as the inverse of content analysis, implying when to use it (to understand the writer) vs. when not (to evaluate content effectiveness). It also provides a recommended sample count (3-5), but does not explicitly name alternative tools or list exclusions.

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