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

Annotations already establish readOnly, idempotent, non-destructive and openWorld, and the description adds genuinely new behavioral context: it fetches remote content, enumerates the exact report contents, and explicitly refuses to render a compliance judgment. It does not cover failure behavior (unreachable link, oversized file, non-PDF response) or latency, which is the remaining gap for a network-fetching tool.

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-loaded with the verb and the full report inventory, then closes with the trigger condition and the exclusions. Every sentence carries information, though the long enumeration in the first sentence makes it denser than ideal for quick scanning.

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?

There is no output schema, so the description must carry the return-value burden and it does: it names each reported signal, including which pages contain undescribed images and which are flagged for human review. For a two-parameter read-only tool, an agent has everything needed to call it and interpret 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 description coverage is 100%, so both `url` (http/https, ≤2048 chars) and `detail` (adds page-by-page list) are fully documented in the schema. The description reinforces 'one PDF' and 'public http or https link' but adds nothing about the `detail` toggle or URL format beyond the schema, so baseline 3 applies.

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 action (downloads one PDF from a public http/https link) and enumerates exactly what it reports: tagged status, title, language, images lacking alt text with page numbers, reading-order/column flags, page count, scanned pages, tables. The resource ('one public PDF') and scope are unambiguous, and it is clearly distinct from the unrelated sibling quote_fix.

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 an explicit trigger ('Use when the user gives a link to a PDF on a public website and asks about its accessibility or screen-reader structure') plus three explicit exclusions: no login-protected files, no modification, no PDF/UA, WCAG or legal compliance verdict. This is the full when/when-not pattern.

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