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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real context by disclosing that the output is component names rather than source or docs, which tells the agent this is a discovery step. It stops short of covering result ordering, empty-result behavior, or what a match means in practice.

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, with the core purpose front-loaded and the example queries and downstream handoff following. No filler, though the parenthetical examples slightly crowd out higher-value guidance about alternatives.

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?

For a simple 3-parameter read-only search with no output schema and full schema coverage, the description covers purpose, matching mode, and the shape of the result. Only minor gaps remain around result behavior and when to bypass this tool entirely.

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 query, tier and limit are already fully documented in the schema, making the baseline 3. The description adds only the notion that the query is natural-language functional description, while tier and limit are left entirely to the schema.

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?

Names a specific verb ('Find') and a specific resource set ('Caliper UI components, blocks and Pro screens') and clarifies the matching is by function rather than name, with concrete example queries. The clause 'Returns names to pass to the other tools' implicitly separates it from fetch-oriented siblings like get_component, though it never names them explicitly.

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?

Clear context is given: use this when you only know what a part does, and the returned names feed the other tools, which establishes the discovery-then-fetch workflow. There are no explicit exclusions or named alternatives telling an agent when to skip this step and call get_component directly.

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