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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond that: exact-match semantics with whitespace, table-cell, dollar-sign and curly-quote tolerance, occurrence handling guidance, and what found=false plus numbers_elsewhere mean. This is real behavioral context an agent cannot get from annotations.

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 core purpose and the usage rule, and the args block is justified here because the schema is bare. It runs somewhat long and restates return values that also appear in the output schema, which is minor redundancy.

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?

Covers all four required parameters, matching strictness, multi-occurrence disambiguation, and the negative-result path, so an agent can call it and interpret it correctly without further hints. Nothing material is missing even with a 0%-described schema.

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 0% and the schema has no param descriptions, so the description carries the full burden — and it does: examples for cik and accession_number, guidance on where filename comes from (content_object or a search result, exhibits included), and a 1000-character cap on quote with formatting advice.

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 concrete verb and resource ('Check that a figure or sentence really appears in a filing document') plus the added value (a highlight link), which is enough for an agent to know what it gets. It does not explicitly distinguish itself from the sibling verify_figure, leaving some ambiguity about which one to pick for pure numeric checks.

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 explicit when-to-use ('Use this before stating any number or quotation from a filing'), explains why a whole-document link is insufficient, and prescribes the correct input shape with examples. It also covers the failure path: if found is false, consult numbers_elsewhere rather than presenting the text as a quote.

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