Photos

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

Annotations only cover the read-only/idempotent safety profile; the description adds the expensive bits they can't: ~550 vs ~1500 tokens per image, images persisting in conversation context, and the paging strategy. This is exactly the context an agent needs before an irreversible context-cost commitment.

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?

Front-loads 'EXPENSIVE' and its cost figures, then conditions, then paging advice. Dense but every sentence carries actionable content; the multi-clause second sentence runs long without losing meaning.

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?

With no output schema, the description fully covers what comes back (images, resolution, token footprint, persistence) plus selection and paging behavior. An agent has everything needed to call this correctly and sparingly.

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 100%, so the baseline is 3, but the description adds genuine strategy beyond the schema: page with offset rather than raising limit, and reserve full_resolution for explicit quality requests or unreadable detail. Only the ad-id format is left entirely to the schema.

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: returns the ad's photos as viewable images, at two resolution/token tiers. It is clearly distinguishable from get_ad, which it names as the text-based alternative.

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?

Explicit when-to-use triggers (renovation/condition, body damage, what is being sold), an explicit when-not (not for every ad of a search page), and a workflow rule (pick 1-3 finalists first). Rival tool get_ad is named as the thing to prefer when text suffices.

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