pocketdraft_inspect_project

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered structurally. The description does add real behavioral context: 'No image bytes' (a return-content limit an agent would otherwise assume wrongly), 'browser-measured pixel bounds' (provenance of the geometry), and that name/text matches are candidates rather than definitive hits. It says nothing about pagination, result size limits, or what happens with a large project.

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?

Four compact clauses, front-loaded with what the tool returns, then filters, then the two critical caveats. Nearly every clause carries information. The telegraphic style is efficient but slightly at the cost of readability.

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?

An output schema exists, so return values need no explanation, and annotations cover the read-only safety profile. The description supplies the filter surface, the no-image-bytes constraint, and the optional full-project toggle. The only real gap is undocumented `exact` and `geometry` parameters, which is minor against an otherwise complete picture.

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 0%, so the description must carry the load. It names most filter parameters (canvasIds, layerIds, kind, name, text) and implies includeProject via 'Full project optional', but never explains `exact` or `geometry`, and the 'candidates' note hints at the exact-match semantics without stating it. Useful but incomplete for an 8-parameter tool with no schema docs.

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 concrete verb ('Read') and enumerates exactly what comes back: current revision, history entries, ordered layers with full styles and browser-measured pixel bounds. That is specific and distinguishable from a plain metadata read. It stops short of naming how it differs from siblings like pocketdraft_history or pocketdraft_preview, so it is clear but not sibling-differentiated.

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?

There is no explicit when-to-use or when-not-to-use guidance and no alternative tool is named, even though pocketdraft_history and pocketdraft_preview overlap on similar data. The one caveat ('names/text only find candidates') is a hint about filter behavior rather than routing guidance. Usage is left to inference.

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