qa_social_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 safety is covered; 'no files written' restates that. The value added is the disclosure that it renders the post and independently inspects contrast, visibility and collisions — a behavioral trait not in the annotations — but it says nothing about what a failure looks like, thresholds used, or whether it mutates nothing at all versus caching a render.

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 compact sentence, front-loaded with the verb and resource, with the caveat appended. It is efficient, though the unexplained 'CP' costs a little clarity for the space saved.

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 tool whose input is a large nested template spec with template-specific requirements (e.g. callouts must be exactly 4, portrait vs scene fields, provenance fields) and which has no output schema, the description does virtually nothing to explain which fields matter or what the inspection returns. It is far too thin relative to the complexity of the call.

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 dozens of properties (template, callouts, maskSmoothing, edgeFeather, cropPolygon, approvedWords, factsVerified). The description contributes no meaning for any of these, so the agent gets only structural constraints and enum lists with no explanation of which fields the measurement depends on.

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 specific actions (measure, inspect rendered contrast, visibility, collisions) on a specific resource (social text), so the general purpose is inferable. However, the abbreviation 'CP' is unexplained jargon and the phrasing 'measure ... text' does not clearly say what artifact is produced or confirmed, leaving the agent to guess at the output of the check.

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?

There is no explicit when-to-use statement and no exclusion or routing to siblings such as validate_social_post or qa_one_pager_layout. The only guidance-like clause, 'no files written', hints at a non-persisting check but never states the precondition (a rendered post must already exist) or when this check is preferable to the validation siblings.

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