Server Quality Checklist

Tool Scores

• list_threat_modelsA
  4.3/5.0
  Behavior5/5

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

  The description discloses significant behavioral traits beyond the read-only and idempotent hints: it explains the sort order (most recently updated first), the exact fields in each entry, the nuanced semantics of `frameworks` (incidence vs. coverage, with a concrete example), and the pagination limitation ('cannot reach past the first page' and 'treat a full page as "at least twenty"'). This goes well beyond the annotations and provides critical usage caveats.

  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 paragraphs but every sentence adds value. It front-loads the main purpose, then details entry fields, clarifies the subtle meaning of `frameworks`, and ends with a critical pagination warning. There is no fluff; the length is appropriate for the tool's complexity. The structure is logical and wastes no 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 is highly complete for a read-only list tool: it covers sorting, fields, the nuanced frameworks metric, and pagination behavior. The output schema (though not shown) is complemented by these explanations. The only missing piece is an explicit explanation of `organization_id`, which is a minor gap. Overall, the tool's behavior is almost fully described, making it easy 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.

  Parameters2/5

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

  The input schema has one optional parameter `organization_id` with no description in the schema (0% coverage). The description mentions 'caller's organizations' but does not explain the effect of `organization_id` on the results, nor clarify that omitting it lists all accessible organizations. This is a notable gap for a tool with zero schema coverage, as the description should compensate but only partially implies the parameter's purpose.

  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 states a specific verb and resource: 'List threat models in the caller's organizations, most recently updated first.' It clearly distinguishes the tool's scope by listing what each entry includes and excludes (name, description, criticality, owner, owning team, last changed, frameworks; but not contents). This is more specific than a generic 'list' and provides exact context.

  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 clear context about when to use this tool: to list threat models with metadata and frameworks, not to retrieve model contents. It also mentions pagination limits ('Returns at most twenty, and cannot reach past the first page'), helping users understand the scope. While there are no explicit alternatives mentioned (no sibling tools), the 'does not carry a model's contents' implies that a different tool would be needed for content access. This is clear context without explicit exclusions.

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