Phos Sales Engine

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

No annotations provided, so description carries full burden. Discloses data sources (Yellow Pages/scrapers) and critical behavior (deduplication against existing DB). Missing: rate limits, idempotency, failure modes, or output structure.

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 efficient sentences with zero waste. Front-loaded with core purpose ('Find business prospects...'), followed by implementation details. Excellent information density.

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?

Good coverage of discovery mechanism and deduplication logic, but lacks description of return values (no output schema exists). For a 4-parameter prospecting tool, should specify what constitutes a prospect or returned fields.

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%, establishing baseline 3. Description reinforces 'industry and location' semantics but doesn't add syntax/format details beyond schema. Geographic constraint (NZ) is already specified in location parameter 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?

Clear specific verb (Find), resource (business prospects), filters (industry/location), and geographic scope (NZ). Distinguishes from siblings: 'generate_outreach' creates content, 'get_pipeline' retrieves existing data, 'score_prospect' evaluates existing prospects, while this discovers new ones.

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?

Lacks explicit 'when to use' guidance, but implies usage through 'deduplicates against existing DB'—suggesting it's for discovering new prospects not already in the system. No explicit contrast with alternatives or prerequisites 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?

Discloses external AI dependency ('Claude AI sales brain') and return structure (subject, body, personalization points). However, lacks disclosure on side effects (does it log/crm?), idempotency, latency implications of AI calls, or error conditions. Carries full burden due to missing 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?

Extremely concise two-sentence structure. Front-loaded with action (Generate...), followed by mechanism and return value. Zero redundancy or marketing 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?

Compensates partially for missing output schema by listing return values. However, omits prerequisites (valid prospect_id source), failure modes, and whether operation is read-only or creates records. Adequate for simple 2-param tool but gaps exist for production use.

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 complete parameter descriptions (api_key, prospect_id). Description uses phrase 'for a prospect' which aligns with prospect_id semantics, but adds no additional constraints, formats, or examples beyond schema baseline.

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?

Clear verb ('Generate') and resource ('outreach message') stated. Mentioning 'Claude AI sales brain' and return structure (subject/body) clarifies scope. Distinguishes from siblings (find/get/score) implicitly through distinct action, though explicit contrast is absent.

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 versus siblings (e.g., whether to call after score_prospect, or how it relates to the pipeline). No prerequisites mentioned despite likely requiring prospect_id from find_prospects.

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 provided, so description carries full burden. Discloses cost behavior ('Free (0 credits)') and hints at return data structure (prospects by stage, conversion rates). Lacks details on rate limits, authentication scope, 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?

Extremely concise with two information-dense fragments. Front-loads the core purpose, follows with cost constraint. No filler words—every element 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?

Adequate for a simple 2-parameter read operation without output schema. Describing the return metrics (prospects by stage, conversion rates, daily metrics) compensates partially for missing output schema documentation.

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% (both api_key and product have descriptions), establishing baseline 3. Description does not add parameter-specific context (e.g., valid product values, API key format), butSchema adequately covers semantics.

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?

Clear verb (Get) + resource (pipeline statistics) with specific details about what metrics are returned (prospects by stage, conversion rates, daily metrics). Implicitly distinguishes from siblings (find_prospects, generate_outreach, score_prospect) by describing aggregate analytics rather than individual prospect operations.

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 cost information ('Free (0 credits)') which informs usage constraints. However, lacks explicit guidance on when to use versus alternatives or prerequisites. Usage is implied by the data scope (aggregate pipeline view vs individual prospect 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 provided, so description carries full burden. Discloses return format (0-100 score, breakdown, contributing factors) which compensates for missing output schema. However, omits mutation details, caching behavior, or rate limiting context typical for API-scoring tools.

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 efficient sentences with zero waste. First sentence states purpose; second discloses return value. Every element earns its place with 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 100% schema coverage and no output schema, the description adequately compensates by detailing return values (score range, breakdown). Lacks only operational context (side effects, persistence) that annotations would typically provide.

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

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

Schema has 100% coverage with both top-level parameters documented ('Your Sales Engine API key' and 'Prospect data to score'). With high schema coverage, baseline 3 is appropriate; description adds no additional parameter semantics but schema is self-sufficient.

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?

Specific verb 'Score' with resource 'prospect' and clear context 'against your Ideal Customer Profile (ICP)'. Distinguished from siblings: find_prospects (discovery), generate_outreach (content creation), and get_pipeline (retrieval) by focusing on evaluation of existing prospect data.

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

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

Implies usage through input requirement (prospect_data) suggesting use when evaluating known prospects, contrasting with find_prospects. However, lacks explicit 'when to use' guidance or workflow positioning relative to generate_outreach or get_pipeline.

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