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

Annotations only declare readOnly/idempotent/openWorld; the description goes well beyond them by defining the ref character grammar (<accession>/<filename>@<start>+<len>), the [calc: ref:..., ref:...] convention, the ~200 KB input ceiling, and the full failure taxonomy (rounded, mismatch, bad_ref, not_derivable, unsourced_numbers) with what each means. An agent knows what the tool will and won't accept before calling.

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 sentence, followed by example-driven syntax, return codes, and a closing instruction — logical order, no filler. Some length is unavoidable for the citation grammar, though the indented inline examples read slightly like formatting artifacts rather than tight prose.

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 return-value explanation isn't strictly required, yet the description still covers input format, failure semantics, size limit, and the follow-up use of linked_text/footnotes. For a one-parameter read-only validator, nothing an agent needs to call it correctly is missing.

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 schema is a bare {text: string} with 0% description coverage, so the description carries the whole burden — and does: it specifies the in-text citation syntax, both ref forms, and the max ~200 KB size. That is more than enough for the single required parameter.

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 opening sentence names a specific verb and resource — check every number in a draft against the filing characters it cites — and adds the linking outcome. It is immediately distinguishable from verify_figure (single figure check) and verify_quote, which it implicitly routes away from by naming them as ref sources.

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 prescribes the exact workflow: write citation refs after each figure, take refs from list_figures or verify_figure, use [calc: ...] for derived numbers, fix all failures before presenting, then use linked_text/footnotes. That is explicit routing and a clear when-to-call. It stops short of stating any exclusion or when-not-to-use case, so it falls just short of a 5.

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