Server Quality Checklist

Tool Scores

• get_archive_healthB
  3.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds that an admin search-engine overview may be included, but it does not explain what triggers 'full mode' or any permission implications of the admin view.

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

  Conciseness4/5

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

  A single, front-loaded sentence that states the primary resource first. It is concise, but 'full mode' is referenced without explanation, which is a minor clarity cost rather than a verbosity problem.

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

  Completeness2/5

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

  With no output schema, the health response shape is left undescribed. The 'full mode / admin search-engine overview' behavior is mentioned but not tied to any parameter or condition, so an agent cannot reliably know how to request it or what it will return.

  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 already documents sourceId at 100% coverage as an optional ingestion source ID. The description adds some meaning by connecting the optional parameter to source health, but the connection is implicit and 'full mode' has no corresponding parameter in the schema.

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

  Purpose4/5

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

  Names a specific action ('Get') and a clear resource: global index health, optional source health, and an admin search-engine overview. It reads as distinct from the sibling get_archive_stats, though 'full mode' is left undefined which prevents a 5.

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

  Usage Guidelines2/5

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

  Provides no guidance on when to choose this tool over siblings such as get_archive_stats, search_emails, or list_ingestion_sources. The only usage hint is that source health is optional, which is closer to parameter guidance than tool-selection guidance.

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

• get_archive_statsB
  3.3/5.0
  Behavior3/5

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

  The annotations already establish readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds a little context about the dual nature of the result (overall dashboard stats plus per-source details), but it does not disclose behavior beyond that, such as what happens with invalid source IDs or whether the response combines both stats types.

  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, efficient sentence with no filler. It front-loads the main action and resource, and every word adds meaning.

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

  Completeness3/5

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

  For a read-only tool with one required parameter, the description is adequate, but with no output schema it leaves the exact contents of 'statistics' unspecified. An agent can invoke the tool correctly, but it cannot fully predict the return shape or determine precisely which metrics are covered.

  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%: the only parameter, sourceId, is documented as 'Ingestion source ID' with a UUID format. The description's phrase 'for one ingestion source' adds little beyond the schema, so it stays at the baseline for fully covered parameters.

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

  Purpose4/5

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

  The description names a specific verb ('Get') and resource ('overall dashboard statistics and detailed statistics for one ingestion source'), which makes the tool's main function clear. It is implicitly different from siblings like list_ingestion_sources or get_email, but it does not explicitly call out how it differs from get_archive_health.

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

  Usage Guidelines2/5

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

  The description gives no direct statement about when to use this tool versus the siblings. There is no mention of exclusions, alternatives, or conditions that would help an agent choose between get_archive_stats and get_archive_health or list_archived_emails_for_source.

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

• search_emailsB
  3.3/5.0
  Behavior3/5

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

  Annotations already provide a strong safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description does not need to cover those. However, it adds no extra behavioral context such as whether only indexed archives are searched, how matching strategies behave, or what the result contains.

  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 with no filler. Every phrase earns its place, and it conveys the core function without redundancy.

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

  Completeness2/5

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

  Given the tool's complexity (16 parameters, no output schema, no parameter descriptions), the description is too thin to fully support correct invocation. It omits details about return shape, pagination defaults, matching strategy semantics, and how filters combine, so an agent would likely need to infer too much.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description only generically references 'full-text search and structured filters' without explaining any of the 16 parameters. It gives little help for choosing or combining parameters like matchingStrategy, sources, searchIn, or date ranges.

  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 and resource ('Search archived emails') and states the mechanism ('full-text search and structured filters'). This clearly distinguishes it from sibling tools like get_email or list_archived_emails_for_source, which are for single retrieval or source-based listing.

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

  Usage Guidelines2/5

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

  There is no guidance on when to prefer this tool over its siblings, nor any exclusions or prerequisites. The description only implies usage by stating what the tool does, leaving the agent to infer when search_emails is the right choice.

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

• list_archived_emails_for_sourceA
  3.6/5.0
  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 the scope constraint ('one ingestion source') but reveals no additional behavioral traits such as ordering, return shape, or pagination behavior. This is adequate but not enriching.

  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 tight sentence that states the action, the object, and the scope with zero filler. Every word contributes meaning, and the most important constraint ('for one ingestion source') is front-loaded.

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

  Completeness3/5

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

  For a straightforward read-only list operation, the description is minimally sufficient, especially with annotations covering side effects. Still, there is no mention of pagination, result ordering, or what an archive email record includes, and there is no output schema to fill that gap.

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

  Parameters2/5

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

  Schema parameter description coverage is only 33%, with page and limit left undocumented. The description clarifies the role of ingestionSourceId but does not mention pagination semantics or defaults, leaving two of three parameters to be inferred solely from their names.

  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 and resource ('List archived emails') and narrows the scope to 'one ingestion source', which cleanly distinguishes it from siblings like get_email or search_emails. The intent is immediately clear without needing to inspect the schema.

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

  Usage Guidelines3/5

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

  The description implies the appropriate use case: retrieve archived emails tied to a single ingestion source. However, it provides no explicit routing or exclusions (e.g., 'use search_emails for filtered queries' or 'prefer get_email for a single email'), so the agent must infer when this tool is preferable over siblings.

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

• get_emailA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral value beyond those by disclosing that the response includes attachments and thread details, which helps the agent set expectations about the returned data without needing an output schema.

  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, focused sentence with no filler. It front-loads the action and resource, then adds return details, making it easy to parse and act on.

  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 fetch-by-ID tool, this is complete: the schema documents the required parameter, annotations cover the safety profile, and the description clarifies what the response contains. Nothing essential is missing for an agent to select and invoke the tool 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%, with the single 'id' parameter clearly described as 'Archived email ID'. The tool description adds the phrase 'by ID' but does not provide additional semantic details beyond what the schema already states, so the 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 action ('Get'), the resource ('one archived email'), and the selection method ('by ID'). Mentioning 'including attachments and thread details' further distinguishes it from sibling tools like search_emails or list_archived_emails_for_source.

  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 'by ID' phrasing provides a clear context for when to use this tool: when the agent already has an archived email ID. It does not explicitly mention alternative tools for unknown IDs, but the contrast with search_emails is strongly implied, making the usage context clear if not exhaustive.

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

• list_ingestion_sourcesA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds useful context: results are permission-scoped to the current API key. It does not detail pagination or response shape, but for a parameterless list operation this is a minor gap.

  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?

  One short, front-loaded sentence with no filler. Every word contributes meaning, and the main action and scope are immediately clear.

  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 parameterless list operation with annotations covering safety, the description is complete: it states the resource, the scope, and the outcome. No additional invocation decisions are needed, and the absence of an output schema is acceptable given the simple list semantics.

  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 no parameters, so the schema fully covers the interface. The description's mention of 'current API key' adds meaningful context about implicit scoping without needing to document any parameter details.

  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?

  States a specific verb and resource: 'List ingestion sources', plus an explicit scope ('accessible to the current API key'). This is clearly distinct from sibling tools that operate on emails, archives, or 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 by scoping results to the current API key's accessible sources, which tells the agent this is an enumeration operation. It does not explicitly name alternatives or exclusions, but the resource name is distinctive enough to make the intended use obvious.

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