qa_one_pager_layout

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the description's 'without writing files' merely reinforces it. It adds real context that measurement uses exact CP font metrics, but says nothing about what is returned (violation list, measured widths, pass/fail) or how failures surface — notable for a QA tool with no output schema.

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?

One sentence, front-loaded with the core action (measure) followed by the second check (required fields) and the side-effect guarantee. No filler, though the compression leaves key terms like 'CP fonts' and 'text slot' unexplained.

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 validation tool with no output schema, the definition should say what a run produces and what counts as a failure; it does not. Annotations cover safety and the purpose is narrow, so the gap is real but not disqualifying — an agent knows what to send and roughly why, just not what comes back.

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% on a single deeply nested content object with nine required children, four cards, three callouts and per-field min/max lengths. The description contributes only 'check required fields', which does not explain how length limits are enforced, what 'draft' vs 'final' mode does, or whether measurement failures block or merely report. The schema's constraints carry nearly all the meaning here.

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 and resource: 'Measure every text slot with exact CP fonts and check required fields'. That is clearly a layout-QA operation on a one-pager, distinguishable from creation tools. It does not name the sibling it supersedes (e.g. qa_social_layout or validate_one_pager_file), so differentiation is only implied by 'one-pager' in the name.

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?

Usage is implied rather than stated: 'without writing files' suggests running this instead of create_one_pager when you only want validation, but there is no explicit when-to-use, no prerequisite (e.g. content must be assembled first), and no routing to qa_social_layout for the social variant. An agent can guess the intent but is given no decision rule.

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