Build / update the app knowledge map

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

Annotations only declare the generic write shape (readOnly=false, idempotent=false, destructive=false); the description adds the genuinely useful behavior — that this writes a persistent JSON artifact at a specific path, that the scan is static across five framework flavors, and that an exploration graph is merged conditionally on sessionId. It does not state whether an existing map is overwritten or diffed, nor the cost of a full re-scan, which keeps it below 5.

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?

A single sentence that front-loads the verb and the output artifact before the framework list, with zero filler. The parenthetical framework enumeration is dense but each item earns its place by telling the agent which project types are supported.

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?

With no output schema and five optional parameters, the description should carry more: it never explains what the resulting map is used for (the query/read/feature_scope siblings) or what the three mode values trade off. It is adequate to identify and invoke the tool correctly, but an agent cannot predict the result or choose a mode confidently.

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 100%, so all five parameters are already documented, and the description's only added semantics — sessionId pulling in the exploration graph — restates the schema text for that field almost verbatim. The mode enum (static_only / runtime_merge / full) is never explained in the description, which is the one place real added meaning was possible.

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?

The description names a concrete verb pair (build/update), a concrete artifact ('.swipium/app-map.json'), and the exact inputs it scans (routes/screens across Expo Router, React Navigation, Android, SwiftUI/UIKit, Flutter). That is far more specific than a tautology. It stops short of 5 because it never distinguishes itself from the sibling 'qa_app_map_update', whose name implies overlapping behavior.

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?

Usage is only implied: the agent can infer 'call this when you need an app map, and pass sessionId to fold in an exploration graph'. There is no explicit statement of when to use this versus qa_app_map_update, qa_app_map_query, or qa_app_map_read, and no prerequisite about first needing an existing session.

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