scan_project

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive, so the safety profile is partly covered. The description still adds valuable context the annotations don't: it never executes project code, it returns findings with file:line references plus fixes, and it never returns source code. It stops short of stating runtime, rate, or permission requirements beyond the schema's path note.

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?

Front-loaded with the purpose, then the coverage list, then the routing to alternatives – logical order. The parenthetical enumeration of store rules and accessibility checks is dense but each item is a concrete area an agent could match a user question against. Slightly overlong as one running sentence, but nothing reads as filler.

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?

No output schema exists, yet the description tells the agent what to expect back (findings with file:line references and fixes, never source code), covers side effects (never runs project code), and covers usage context. Nothing an agent needs in order to call it correctly or interpret results is missing.

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%, with enum values and defaults fully documented for all three parameters, so the schema carries the burden. The description adds no per-parameter guidance of its own; the only inferable link is that the offline parameter relates to network-dependent checks, which the schema already states explicitly. Baseline 3 is appropriate.

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?

Opens with a specific verb+resource ("Health check for a React Native or Expo project") and then enumerates the concrete domains covered: upgrade blockers, store rules, crash risks, accessibility, MASVS, secrets, malware. An agent can tell exactly what this does and how it differs from security_audit, upgrade_readiness, and check_library without opening any schema.

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?

Explicitly states the use case ("general 'how healthy is this app' question; covers every area at a glance") and names both alternatives with their selecting conditions: security_audit for deeper attacker-prerequisite review, upgrade_readiness for upgrade decisions. It even adds a proactive trigger ("run it before installing or starting a project you did not write").

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