Query the app knowledge map

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

With readOnlyHint=true and openWorldHint=false already declaring a safe, closed-world read, the description's added value is the return shape: ranked results with sources plus a suggested next tool call. It does not disclose whether the map must first be built, how sessionId or projectRoot affect scope, or any pagination/ranking caveats, leaving real behavioral gaps.

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, front-loaded with the capability and followed by the return contract; no filler. Brevity here costs coverage rather than padding.

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?

It covers what the tool does and what it returns for a 5-parameter, no-output-schema tool, but for a search tool with an intent enum, a limit, and session/project scoping, the definition is thin. An agent can call it with a bare query but cannot reason about the optional parameters or prerequisites.

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?

Should score low: 5 parameters with 0% schema description coverage, and the description only maps 'natural-language query' to the query parameter. limit, intent, sessionId, and projectRoot receive no meaning at all, so the description fails to compensate for the coverage gap.

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 resource ('Search the app map') and enumerates the indexed content types (features, screens, code, tests), which distinguishes it from map-mutating siblings like qa_app_map_build or qa_app_map_update. It falls short of naming the nearest alternative (qa_app_map_read) explicitly, so an agent still infers the boundary.

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?

The word 'Search' together with 'natural-language query' implies discovery-style usage, and 'suggested next tool call' hints at chaining into a follow-up tool. However, there is no explicit when-to-use/when-not guidance and no mention of when a structured read or feature-scope call would be preferable.

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