capture

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

With no annotations, the description carries the full burden and does real work: it discloses the viewport (phone width), the deterministic output path (assets/<id>.png), and the annotation behavior of boxing the matching sentence, including the empty-match fallback that boxes the title. It omits whether an existing asset is overwritten and whether the page load is awaited before capture.

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, front-loaded with the action and output, with the parameter guidance tucked into parentheticals rather than a separate paragraph. Dense but every clause carries information; only the nesting of match guidance mid-sentence slightly hurts scannability.

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 4-param tool with no annotations and no output schema, the description covers viewport, output path, and match semantics well. However, the project parameter is undefined and there is no statement about return value, overwrite behavior, or failure modes such as an unmatched phrase.

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 coverage is 0%, so the description must compensate, and it does for three of four params: id maps to the filename, url is the page, and match gets genuinely useful guidance (short exact phrase, 8-20 characters safest, empty boxes the title) that no schema field conveys. The project parameter is never mentioned, which is the remaining gap.

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?

States a specific verb (screenshot) and resource (a web page at phone width) plus the exact output location assets/<id>.png, so the effect is unambiguous. It does not differentiate itself from similarly-named siblings like render or preview, leaving the agent to infer which produces a static evidence capture.

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?

The phrase 'as evidence asset' hints at a review/evidence workflow, but there is no explicit when-to-use, when-not-to-use, or named alternative among preview, render, or draw. The agent must guess whether this or render is the right tool for a given page.

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