Server Quality Checklist

Tool Scores

• get_domain_statsA
  4/5.0
  Behavior3/5

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

  Annotations already declare this as a read-only, idempotent, non-destructive operation. The description adds value by specifying the statistical components returned, but it doesn't disclose additional behaviors such as handling of unknown domains or data freshness. No contradiction with annotations.

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

  Conciseness5/5

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

  Two concise sentences, front-loaded with the tool's purpose and immediately followed by an example use case. No wasted words.

  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?

  For a single-parameter read-only stats tool, the description covers purpose, usage, and expected output metrics. Although there is no output schema, the listed metrics give the agent a reasonable expectation. Missing return structure details but adequate given the tool's 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?

  The input schema fully documents the single 'domain' parameter with a clear description, giving 100% coverage. The tool description does not add further parameter semantics beyond the schema, but the schema suffices.

  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 function with a specific verb ('Get') and resource ('detailed statistics for a domain'), enumerating the exact metrics returned. It differentiates from sibling tools like list_errors_by_domain by framing the output as a trust assessment for domain data.

  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 explicitly states the intended use case: 'Use this to assess how trustworthy deadends.dev data is for a domain.' This provides clear context for when to choose this tool over error-listing siblings, though it doesn't mention exclusions or when not to use it.

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

• get_error_chainA
  4/5.0
  Behavior3/5

  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 safety profile is covered. The description adds behavioral context by listing the three relationship types (leads_to, preceded_by, confused_with), similar to how a date-range constraint adds value. It does not disclose any additional caveats, but annotations sufficiently cover the basics.

  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 three sentences, front-loaded with the action verb 'Traverse' and immediately explains the output structure. Every sentence earns its place: purpose, output details, and when to use. No fluff or redundancy.

  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?

  For a read-only graph traversal tool with a single parameter, the description sufficiently explains what the tool returns (leads_to, preceded_by, confused_with) and when to use it. No output schema exists, but the description covers the return content. It could benefit from noting any pagination or limits, but for this simple tool, the context is complete enough.

  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 input schema provides 100% coverage for the single parameter error_id, so the schema already documents the parameter. The description does not add extra syntax or format details beyond what is in the schema. Baseline 3 is appropriate since the schema carries the burden.

  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 a specific verb ('Traverse') and resource ('error transition graph'), clearly distinguishing it from siblings like lookup_error or get_error_detail by explaining the graph relationships (leads_to, preceded_by, confused_with). This makes the tool's unique purpose unmistakable.

  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 explicitly states when to use the tool: 'Use this to diagnose cascading failures and predict what comes next.' It does not explicitly mention alternatives or exclusions, but the context is clear. A 4 is appropriate because it provides clear use case guidance without naming alternatives.

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

• list_errors_by_domainA
  4/5.0
  Behavior3/5

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

  Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds that it returns fix rates and lists all errors in a domain, but does not disclose additional behaviors like sorting or result limits. This is minor but acceptable given the 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.

  Conciseness5/5

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

  Two sentences: the first states the action, the second states the use case. No wasted words, front-loaded with the core purpose.

  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?

  For a simple list operation with 2 parameters and no output schema, the description provides sufficient context: what it lists (errors with fix rates) and why to use it (coverage check). It doesn't go into return format details, but the simplicity and schema coverage make this acceptable.

  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%, so the schema fully documents both parameters. The description's mention of 'specific domain' aligns with the domain parameter but adds no new semantic detail beyond the schema.

  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?

  Description states a specific action: 'List all errors in a specific domain with their fix rates.' This clearly distinguishes it from siblings like lookup_error (single error), list_error_domains (domains only), and search_errors (search).

  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?

  Provides clear context: 'Use this to understand coverage for a domain before relying on it.' This suggests when to use the tool, though it doesn't explicitly mention 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.

• lookup_errorA
  4/5.0
  Behavior3/5

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

  Annotations already mark the operation as readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds that it returns dead ends, workarounds, and error chains and notes domain coverage, but does not disclose additional behavioral traits such as rate limits or no-match behavior. Since annotations cover the safety profile, 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.

  Conciseness5/5

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

  Three sentences, front-loaded with the core action, and every sentence carries information: purpose, return types, usage timing, domain coverage, and a pointer to a sibling tool. No wasted words.

  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 explains the tool's purpose, return categories, usage timing, and domain coverage, and references a sibling tool for more information. For a lookup tool with no output schema and only two parameters, this is fairly complete. Minor gaps include what happens if no match is found, but that is acceptable.

  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%, with both error_message and format described. The description does not add syntax details beyond the schema; it only contextualizes that error_message comes from '51 domains,' which is minor added meaning. Baseline 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 'Match an error message against deadends.dev's database of known errors' with a specific verb and resource. It lists return categories (dead ends, workarounds, error chains) and distinguishes itself from siblings like list_error_domains or get_error_detail, which have 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 Guidelines4/5

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

  Explicitly instructs 'Use this BEFORE attempting to fix any error to avoid wasting time on approaches that are known to fail,' providing clear when-to-use context. It also points to list_error_domains for full domain lists, though it does not explicitly exclude alternatives like search_errors, so it lacks a when-not-to-use.

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

• report_outcomeA
  4/5.0
  Behavior3/5

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

  Annotations provide readOnlyHint=false, destructiveHint=false, idempotentHint=false, which are neutral. The description adds that the call 'improves fix_success_rate and confidence' and 'helps improve the database,' indicating a write side effect. However, it does not disclose potential failure modes, authentication needs, or rate limits. With annotations present and not contradicted, the description adds moderate value beyond the structured metadata.

  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?

  Three concise sentences: the first states the core purpose, the second explains when to call and why, and the third lists the accepted parameters. No filler or redundant information. The structure is front-loaded with the primary action.

  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, no output schema, and a nested object parameter (environment), the description covers the when and what adequately. It does not explain return values, but for a feedback submission tool this is less critical. It could mention that repeated reports may overwrite or update existing records, but the overall context is sufficient for an agent to invoke correctly.

  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%, so all parameters have meaningful descriptions. The description restates the three key parameters (error_id, workaround_action, success) but does not add much depth beyond that. Since the schema already documents each parameter, the description's contribution is marginal but not redundant.

  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 specific action: 'Report whether a workaround from deadends.dev worked or failed.' It identifies the resource (workaround outcome) and the verb (report), distinguishing it from the sibling lookup/list tools which are all read-only. The purpose is unambiguous.

  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 gives explicit timing guidance: 'Call this AFTER applying a workaround' and explains why (to improve the database and fix_success_rate). While it does not name alternatives, the sibling tools are all read-oriented, making it clear this is the only feedback/reporting tool. The context is sufficient for correct usage.

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

• batch_lookupA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, which establishes a safe, read-only operation. The description adds behavioral context beyond this by stating that it returns the best match for each error, implying a per-input result mapping. Given the annotations cover the safety profile, the description provides sufficient additional transparency about the outcome.

  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 concise sentences. The first sentence front-loads the purpose and output behavior, the second explains when to use the tool. There is no filler or redundancy; every sentence 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?

  For a simple tool with one parameter and no output schema, the description covers the core purpose, usage context, and return behavior. It does not detail the exact representation of 'best match' or how errors are handled, but these are not critical for this tool's context. Overall, it is complete enough for an agent to use correctly.

  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 description covers 100% of the parameter (error_messages) with type, maxItems, and a clear description. The tool description adds only general phrasing ('Look up multiple error messages at once') that restates the array nature, but does not provide new semantic detail. With full schema coverage, baseline 3 is appropriate.

  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 function: 'Look up multiple error messages at once'. It uses a specific verb ('look up') and resource ('multiple error messages'), and distinguishes from the single-error sibling lookup_error by emphasizing batch processing. The phrase 'Returns the best match for each error' further clarifies the core behavior.

  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 explicitly provides a usage context: 'Use when debugging a chain of errors or analyzing a log with multiple failures.' This gives clear when-to-use guidance. However, it does not mention alternatives or when not to use it (e.g., for a single error, use lookup_error), so it does not fully meet the 'when-not/alternatives' criterion.

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

• get_error_detailA
  4.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which covers the safety profile. The description adds useful context about the response content (dead ends, workarounds, error chain info, source evidence), but it does not disclose additional behavioral traits like pagination or error handling. This 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 a single front-loaded sentence that efficiently conveys the purpose and key details. It includes an example and a list of what the response contains without unnecessary words.

  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?

  For a simple single-parameter read-only tool with no output schema, the description is complete enough. It specifies the input format and what the response includes, though it does not describe the response structure explicitly. This is adequate given the tool's simplicity and the presence of annotations.

  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 already documents the single parameter error_id with a description, providing 100% coverage. The description enhances this by giving a concrete example ('python/modulenotfounderror/py311-linux'), which clarifies the expected format beyond the schema's generic 'domain/slug/env'.

  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 verb ('Get'), resource ('full details for a specific error'), and scope (by ID), with an explicit example ID format. It distinguishes itself from sibling tools like list_errors_by_domain and search_errors by emphasizing 'full details' and enumerating specific content (dead ends, workarounds, error chain info, source evidence).

  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 clear usage: use this tool when you have a specific error ID and need comprehensive details. However, it does not explicitly exclude alternatives such as lookup_error or get_error_chain, so the guidance relies on implication rather than direct comparison.

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

• list_errors_by_countryA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare read-only, idempotent, and non-destructive. The description adds context about the content returned (visa, banking, legal, etc.) and the scope, which is helpful. 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?

  Two sentences, front-loaded with the primary action and scope, followed by return details and usage guidance. No wasted words.

  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?

  With good annotations and full schema coverage, the description adequately describes what the tool does, what it returns, and when to use it. Could mention the optional domain filter, but schema covers it, so not a significant gap.

  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 has 100% coverage of both parameters. Description reinforces country parameter with examples but doesn't add substantial meaning beyond schema. Baseline 3 is appropriate.

  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 specifies the action (list), the resource (country-scoped dead ends), and the scope (given country). It also differentiates from sibling tools like list_errors_by_domain by focusing on country jurisdiction.

  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?

  Provides explicit usage guidance: use when an AI agent needs jurisdiction-specific knowledge that global LLM training data won't reliably cover. It doesn't explicitly mention alternatives, but the context is clear.

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

• get_country_summaryA
  4.3/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds valuable context beyond annotations by explaining the tool's output structure (total entries, domain breakdown, etc.) and its intended purpose (coverage assessment), giving the agent a mental model of behavior without contradicting any annotation.

  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 core action and a bullet-like list of outputs. Every sentence contributes meaning—no fluff or repetition of schema/annotations.

  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?

  The tool is simple (one parameter, no output schema), and the description fully covers what the summary contains and when to use it, serving as an adequate return-structure guide. Given the lack of an output schema, the description compensates by listing the key fields. No critical context is missing.

  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 input schema already provides a full description for the only parameter ('ISO 3166-1 alpha-2 country code, lowercase'), achieving 100% schema description coverage. The tool description adds no parameter-specific details, so the baseline of 3 is appropriate.

  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 a specific verb ('Get') and clearly identifies the resource ('country-level summary') while enumerating the contents (total entries, domain breakdown, average fix rate, most-recent updates). It is distinct from sibling tools like list_errors_by_country or get_domain_stats, which focus on different granularities.

  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?

  Provides a clear use case: 'Use this to assess coverage for a country before relying on deadends.dev for trip / business / legal planning advice.' This tells the agent when to invoke the tool, though it doesn't mention alternatives or when not to use it. Absence of exclusions aligns with a score of 4.

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

• list_error_domainsA
  4.3/5.0
  Behavior3/5

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

  Annotations already provide safety profile (readOnly, idempotent, non-destructive). The description adds coverage and category context, but not details like ordering or response format; annotations carry most burden.

  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?

  Two concise sentences, immediately stating the action and scope with no filler.

  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 zero-parameter list tool with strong annotations, this description fully conveys what is listed and the breadth of coverage; return values are implied.

  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?

  No parameters exist, so description needs no parameter explanation; baseline for zero parameters is 4.

  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 lists all error domains and counts, specifying the database and scope, which distinguishes it from sibling tools like list_errors_by_domain and get_domain_stats.

  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?

  Provides clear context that this returns the full set of domains, appropriate when a comprehensive overview is needed, but does not explicitly 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.

• search_errorsA
  4.4/5.0
  Behavior4/5

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

  Annotations already disclose readOnly/idempotent/destructive traits. The description adds behavioral depth by explaining the fuzzy matching behavior and the 'across all domains' scope, which is not inferable from annotations or schema alone. It does not go into details about result ordering or pagination, but that's acceptable given the safety annotations.

  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, with the primary purpose front-loaded. It provides the key differentiator and usage guidance without any filler or redundancy. Every sentence 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?

  For a search tool with three parameters and no output schema, the description adequately covers what it does, when to use it, and how it contrasts with similar tools. It doesn't explicitly describe the return format or pagination, but the limit parameter and the use case imply a list of errors. Given the annotations and schema richness, the description is sufficiently complete.

  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 input schema already has 100% coverage with detailed parameter descriptions (e.g., 'query' mentions examples, 'limit' notes default, 'domain' explains optional filtering). The description reinforces these but does not add new meaning beyond the schema; it focuses on usage context rather than parameter specifics.

  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 'Search errors by keyword across all domains', specifying the action, resource, and scope. It explicitly distinguishes itself from 'lookup_error' by contrasting fuzzy keyword search with regex matching, which separates it from a sibling tool.

  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?

  Provides explicit guidance on when to use this tool: 'Use when you have a vague description like ‘memory issues’ or ‘permission denied’ rather than an exact error message.' It also contrasts with lookup_error, giving a clear alternative and the distinguishing heuristic.

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