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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it discloses the four fields searched and confirms the whole captured corpus is scanned, which tells the agent what recall to expect.

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 sentences, front-loaded with the core action and scope, with the filtering and example-query detail following. No filler, though the second sentence's three examples are slightly padded.

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 read-only keyword search with no output schema and full schema coverage on 4 optional parameters, the description supplies what an agent needs to select and call it. It omits any note on result ordering or return shape, but those are marginal for this tool class.

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 every parameter including the q-omit behavior, limit range, and product id example is already documented in the schema. The description's "Filter by product or kind" restates schema content rather than adding syntax or semantics, so the baseline 3 applies.

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 specific verb and resource ("Search every captured screen") and scopes the search surface to titles, notes, page sections, and observed actions. It implicitly separates itself from get_screen/get_screen_image by being a keyword search rather than an id lookup, but it never names those siblings, so the differentiation is left to inference.

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 gives concrete usage context with example queries ("pricing page", "empty state", "date picker") and states the two filter axes (product, kind). It does not state when to prefer a different sibling (e.g., pick_reference or get_screen), so there are no explicit exclusions.

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