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

With no annotations, the description carries the burden and does real work: it discloses that image URLs are signed and expire after 7 days (a critical operational detail an agent would otherwise trip on) and that the call is free. It does not say whether repeated calls are safe or whether images continue to appear over time, but the expiry and cost facts are the substantive ones.

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?

A single dense sentence plus a short endpoint-equivalence clause; the most decision-relevant facts (scope, signed URLs, free) are front-loaded. Slightly overloaded with the return-field list in parentheses, but not wasteful.

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?

An output schema exists, so enumerating returned fields (url, width, height, words, words_checked, cost_usd) is partially redundant, while the genuinely under-covered area — required parameters and auth — is untouched. Adequate for a simple GET, but not complete.

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% for two parameters (call_id, api_key), so the description should compensate. It only obliquely implies call_id via the endpoint path and says nothing at all about api_key — where it comes from, whether it is required, or how it relates to authentication.

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 the resource (thumbnails for a call) and what it returns, and anchors it to the REST endpoint GET /v1/thumbnails/{call_id}, which makes the operation unambiguous. It never names the adjacent siblings (make_thumbnails, recreate_thumbnail, search_thumbnails, edit_thumbnail), so differentiation is left to inference from 'every image so far'.

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 statement of when to call this versus make_thumbnails, search_thumbnails, recreate_thumbnail, or edit_thumbnail. 'Free' hints at a cost tradeoff but the description never turns it into guidance (e.g. 'use this to poll results before re-generating').

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