Server Quality Checklist

Tool Scores

• structure_cold_pitchA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It does disclose a conditional behavior ('If omitted, the response reminds you: no signal, no pitch'), which is useful. However, it does not state whether the tool is read-only, side-effect-free, or what happens on invalid input. The description is adequate but not rich.

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

  Conciseness5/5

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

  The description is two sentences, front-loaded with the primary output and target types. Every word earns its place, and there is no repetition of schema information beyond the enum list, which is also relevant context.

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

  Completeness4/5

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

  Given the absence of an output schema and annotations, the description covers the main output components (structure + swap variables) and a key behavioral rule about signal_found. It is fairly complete for a non-destructive tool, though it could mention error handling or the exact format of the response.

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

  Parameters3/5

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

  Schema coverage is 50%, so the description must compensate. It lists the valid target_type values (though these are already in the enum) and indirectly explains signal_found's role via the 'If omitted' note. This adds some meaning beyond the schema but does not fully clarify the parameters beyond what the schema already provides.

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

  Purpose5/5

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

  The description clearly states the tool's action ('Get') and its specific output ('HOOK / BRIDGE / SOFT ASK structure plus the 4 swap variables'), and enumerates the valid target types. This distinguishes it from sibling tools like audit_cold_message or build_followup_ladder, which focus on different aspects of outreach.

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

  Usage Guidelines4/5

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

  The description implies use when preparing a cold pitch for one of the listed target types, but it does not explicitly say when not to use it or mention any alternatives. It gives clear context but lacks direct exclusions.

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

• build_followup_ladderA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full responsibility. It uses 'Returns' which clearly indicates a read-only, side-effect-free operation. The description also adds context about the statistical impact of the break-up, but doesn't explicitly state safety or permissions; still, for a simple retrieval tool, this is adequate.

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

  Conciseness5/5

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

  The description is two sentences, front-loaded with the main function and including the specific steps. The second sentence adds motivational context without bloat. Every word earns its place.

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

  Completeness4/5

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

  Given the simple nature of the tool and the absence of an output schema, the description sufficiently explains what is returned: a 5-step ladder with moves and rules. It also provides the optional parameter via the schema. It could have detailed the output structure slightly more, but it's complete for its simplicity.

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

  Parameters3/5

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

  Schema description coverage is 100% and fully explains the optional target_type parameter, including its enum and purpose. The tool description does not mention the parameter, but since the schema already provides complete semantics, the baseline of 3 applies.

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

  Purpose5/5

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

  The description clearly states the tool 'Returns the 5-step follow-up ladder' and enumerates the exact steps, making the purpose obvious. It distinguishes this from sibling tools like handle_reply or structure_cold_pitch by focusing specifically on generating a follow-up sequence.

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

  Usage Guidelines4/5

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

  The description implies when to use this tool: whenever a follow-up sequence is needed. It provides useful context with the statistic about deal close rates, but it does not explicitly mention alternatives or situations where it should not be used, hence not a 5.

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

• audit_cold_messageA
  4.3/5.0
  Behavior4/5

  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 discloses the return behavior (PASS/FAIL with named violations and rewrite recipe) and lists the specific rules it enforces. Though it doesn't explicitly state that it modifies nothing, the term 'audit' implies a read-only operation.

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

  Conciseness5/5

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

  The description is a single, well-structured sentence that front-loads the core action, then lists the key rules and return format. No filler words or redundant phrases.

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

  Completeness5/5

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

  Given that there is no output schema, the description adequately covers the return format and criteria. It explains what inputs are expected (a drafted message) and what to expect as output, making the tool's usage fully self-contained despite the optional target_type parameter not being mentioned in the description.

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

  Parameters3/5

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

  Schema coverage is 100%, with both parameters already described in the input schema. The description adds no additional parameter-level detail, which is acceptable given the schema's completeness; the rule list is about message content rather than parameter usage.

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

  Purpose5/5

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

  The description clearly identifies the tool's function with a specific verb ('audit') and resource ('a drafted cold message'). It enumerates the exact rules checked, distinguishing it from sibling tools like structure_cold_pitch or detect_red_flags.

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

  Usage Guidelines4/5

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

  The description implies usage context: it is for auditing an already-drafted cold message, while siblings handle other stages (replying, pricing, structuring). It does not explicitly mention when not to use it or name alternatives, but the context 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.

• detect_red_flagsA
  4.3/5.0
  Behavior4/5

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

  Without annotations, the description carries the burden of disclosing behavior. It states it 'Returns flags found and a CLEAN/CAUTION/WALK verdict,' which outlines the output clearly. The 'Scan' wording implies a read-only operation, though it doesn't explicitly state side-effect freedom. 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.

  Conciseness5/5

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

  The description is two sentences: the first identifies the action and scope, the second specifies the return value. Every word adds value, and it is front-loaded with the core functionality.

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

  Completeness5/5

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

  For a simple one-parameter tool with no output schema or annotations, the description is complete: it covers the input (prospect's reply/brief), the process (scan for signals), and the output (flags + verdict). No significant gaps.

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

  Parameters3/5

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

  The schema has 100% description coverage for the single 'text' parameter. The description repeats the 'reply or brief' context without adding further parameter-level detail, so it meets the baseline for schema-heavy design without extra value.

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

  Purpose5/5

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

  The description clearly states the tool's purpose with a specific verb ('Scan') and resource ('prospect's reply or brief'), and enumerates the exact red flags detected (exposure-pay, spec-work, pay-on-performance, budget mismatch, scope-creep probes). This makes it distinct from sibling tools like handle_reply or audit_cold_message.

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

  Usage Guidelines4/5

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

  The description implies when to use the tool: when you have a prospect's reply or brief and want to check for walk-away signals. It provides clear context but does not explicitly mention exclusions or alternatives for contrast, though the unique purpose reduces ambiguity.

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

• get_full_packA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description assumes the full burden. It clearly states the tool returns a complete bundle of components and lists them. It does not mention return format or size, but for a no-parameter getter that simply returns data, the behavior is sufficiently transparent.

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

  Conciseness5/5

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

  The description is compact: two sentences that front-load the action ('Returns the complete engine'), enumerate the contents, and provide a use case. Every word adds value, and the structure is clear and efficient.

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

  Completeness4/5

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

  The description covers what the tool returns and when to use it, which is important given there is no output schema or annotations. It could have specified the return format (e.g., string, JSON), but the enumerated components give a strong sense of the output, making it largely complete for this simple tool.

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

  Parameters4/5

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

  The tool has zero parameters, so the input schema is empty. According to the rules, a baseline of 4 applies for 0 params, and the description does not need to compensate for missing parameter details. No parameter-related gaps exist.

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

  Purpose5/5

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

  The description uses the specific verb 'Returns' and enumerates the exact contents ('core rules, all target packs, follow-up ladder, reply playbook, pricing menu, red flags'), clearly distinguishing this tool from siblings that handle individual components. It is evident what the tool does and what it returns.

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

  Usage Guidelines4/5

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

  The description provides an explicit use case: 'Useful for full agent context (e.g. a Claude Project system prompt).' This tells when to use the tool, especially in contrast to the more focused sibling tools. However, it does not name alternatives or explicitly state when not to use it, so it falls slightly 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.

• handle_replyA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It clearly frames the tool as a pure analysis function (returns interpretations) with no side effects, and it specifies the four output components. It does not mention edge cases or error behavior, but for a single-enum lookup tool this is adequate.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence that states the purpose and then lists the valid inputs. Every word earns its place; there is no filler or repetition.

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

  Completeness5/5

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

  For a tool with one simple enum parameter and no output schema, the description fully covers the input enum and describes the conceptual output (meaning, next move, reply shape, trap). It is self-contained and gives the agent enough to invoke it correctly.

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

  Parameters4/5

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

  Although the schema description coverage is 0% (the description does not name the parameter), the description lists all allowed reply types, which exactly matches the enum values in the schema. This effectively communicates what the parameter should be, and the context implies those are the valid inputs.

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

  Purpose5/5

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

  The description explicitly states that given a reply type it 'returns what it means, the next move, the reply shape, and the trap to avoid,' which is a specific verb and clear resource. The enumeration of reply types distinguishes it from the sibling tools like detect_red_flags or build_followup_ladder.

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

  Usage Guidelines4/5

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

  The opening phrase 'Given the type of reply received' clearly establishes the context for when to use this tool. However, it does not explicitly mention when not to use it or suggest alternative tools, so it falls slightly short of a full 5.

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

• build_pricing_menuA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It transparently discloses the tool's output (menu structure, scoping questions, negotiation rule) and a key usage constraint (never in cold messages). Though it doesn't explicitly state there are no side effects, the word 'Returns' implies a read-only behavior, which is sufficient for this simple tool.

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

  Conciseness5/5

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

  The description is two sentences: the first lists the three output components, the second states usage timing. Every word adds value, with no redundancy or filler.

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

  Completeness4/5

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

  Given the tool's simplicity (one parameter, no output schema), the description covers what it returns, how it uses the parameter, and when to use it. It doesn't provide example output or elaborate on the scoping questions, but that's likely sufficient for an agent to invoke it correctly in context.

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

  Parameters4/5

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

  The schema has 0% description coverage, and the description partially compensates by mentioning 'for the target type,' indicating that the output varies based on target_type. It could explain how to choose among enum values, but the enum names are self-explanatory in context, making the parameter's role reasonably clear.

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

  Purpose5/5

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

  Clearly states the tool returns a 3-option menu structure, scoping questions, and a negotiation rule. The verb 'Returns' plus the specific components distinguishes it from sibling tools like structure_cold_pitch or build_followup_ladder, which serve different purposes.

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

  Usage Guidelines5/5

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

  Explicitly provides usage timing: 'Use only after the prospect asks about price — never in a cold message.' This gives both a positive and negative condition, making it clear when the tool should be invoked versus avoided.

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