mobbin_search_screens

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

Annotations already declare readOnly, openWorld, non-idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: it hits the live API, needs an API key, and does not persist results. The platform-filter limitation is also a real behavioral caveat; only the ambiguity of the phrasing keeps this from a 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?

Three short clauses, front-loaded with the core action and no filler. The clause 'current native filter supports iOS, not Android' is terse to the point of ambiguity about whose filter is meant (the MCP wrapper or the Mobbin API), which slightly undercuts an otherwise efficient description.

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, so the description should say more about what screens look like, yet it gives no shape for the results. Combined with 0% schema coverage and an unclear android-vs-iOS constraint, an agent can call the tool but cannot confidently predict the response or the query syntax.

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 all three parameters (query, platform, limit) are unnamed and undocumented in the schema, and the description must compensate. It partially covers 'platform' via the iOS-only note, but says nothing about what a valid query looks like or what limit controls. This is a substantial gap for a 3-parameter tool.

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 gives a concrete verb and resource: it queries the official Mobbin REST screen search live. It is distinguishable from the general-purpose mobbin_call and from search_apps, though it doesn't explicitly name the sibling it replaces. The scope is clear enough that an agent can tell what the tool returns (Mobbin screens).

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?

It states a precondition ('Requires your API key') and one usage caveat ('current native filter supports iOS, not Android'), but it never says when to choose this over mobbin_call or mobbin_list_tools. The iOS-only note also sits ambiguously beside a schema enum that still accepts 'android', so the agent is left to infer which is authoritative.

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