get_comparison

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

With no annotations provided, the description carries the full burden. It discloses that results may include processing status (polling), that signed URLs are refreshed, that visual artifacts may or may not be available, and that the operation does not consume credits. These are meaningful behavioral traits beyond the bare 'get' operation.

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?

The description is two sentences, front-loaded with the core purpose, and every clause adds useful information. There is no repetition of schema fields or fluff; the second sentence gives actionable usage guidance. Highly concise and well-structured.

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 single-parameter tool with no annotations and no output schema, the description covers the key aspects: what it returns (including conditional visual data), when to use it (polling and re-fetching), and cost behavior. It is sufficiently complete for an AI agent to select and invoke the tool correctly.

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?

The input schema fully documents the only parameter (comparison_id as UUID, 100% coverage). The description merely references 'by its ID' without adding any new semantic detail about the parameter itself. Baseline 3 is appropriate because the schema already handles this.

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 opens with a specific verb-resource pair ('Get the status and results of a specific comparison by its ID') and elaborates on the exact contents (visual.status, visual.manifest contract, grouped change identities, salience metadata). This clearly distinguishes it from sibling tools like list_comparisons or get_text_diff.

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 description explicitly states when to use the tool: 'to poll a comparison that is still processing, or to re-fetch results (including fresh signed URLs) for an existing comparison.' It also notes 'Does not consume credits,' which is a relevant selection factor. It does not name alternatives or provide explicit when-not guidance, so it misses the '5' threshold.

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