Swift app audit context

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, covering the safety profile. The description adds that the bundle is built from *local* data and is 'audit-grade,' which lightly corroborates the offline, repeatable behavior, but it discloses nothing further (e.g. scope of results, cost, determinism of the bundle) beyond what annotations provide.

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 tight sentences with the artifact and its inputs front-loaded and the usage timing second. No filler or restated name/title.

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?

For a 9-parameter, zero-required composite aggregator with no output schema, the description supplies enough to invoke it (what it builds, from which sources, when to use it). It leaves the shape of the returned bundle unstated, but with no output schema and annotations covering safety, that gap is minor.

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 description coverage is 78% and the schema already documents focus, format, feature, symptom, year_min, platforms and frameworks. The description echoes the feature/platform/symptom mapping (matching three params) but adds no new syntax, defaults, or constraints, so the baseline 3 applies.

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?

States a specific verb and artifact ('Build an audit-grade ... research bundle') and names the four data sources it draws from (WWDC, HIG, tutorials, Swift Evolution), which implicitly positions it as the composite aggregator over the granular siblings. It does not explicitly contrast itself against tools like wwdc_search or apple_hig_search, so differentiation stays implicit.

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?

'Use before code changes to map feature/platform/symptom to evidence and validation steps' gives a clear triggering context and success intent. No when-not guidance or explicit naming of the alternative single-source tools, so it stops 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.