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

Annotations only declare that this is a safe read; the description adds real behavioral detail the agent could not otherwise know: newest-first ordering, a fixed 24-per-page size, and the non-obvious asymmetry where only the first 4 ready frames return a preview image and full-size url as text while later frames carry the url in structuredContent only. It also explains the pagination envelope and the page + 1 continuation rule.

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?

Purpose is front-loaded in the first clause, followed by return shape, usage, filters, and pagination in a logical order with no filler. The middle sentence is densely packed with clauses about preview images versus structuredContent urls, which costs a little readability but earns its space given there is no output schema.

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 available, the description takes on the full burden of explaining return values and does so: page, page_size, total, per-item fields, and the split between text url output and structuredContent. Pagination, ordering, and page size are all covered, so an agent has everything needed to call it and consume the result.

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 workflow meaning beyond the schema by naming which parameters act as filters (product_id, status, approved) and by prescribing the pagination loop with page + 1. It does not restate enum or format details, which is correct given the schema already carries them.

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 ('Lists the store's shoots') and immediately disambiguates the domain jargon by explaining that each result image is a frame. It also enumerates the returned fields and the sort order, which lets an agent separate it from 'get_shoot' (single) and 'list_products' without opening the schema.

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?

Gives two concrete use cases ('check on a shoot', 'find frames to approve') and names the three filters that narrow results. It stops short of explicitly routing to alternatives such as get_shoot for a single shoot or approve_frame for the follow-up action, so it is clear but not fully comparative.

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