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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds real context beyond that: results are restricted to the LATEST snapshot (not historical), the 'indexed' date is defined as the date an index added a report lacking a publication date, and the SHA-256 identifies the exact file version used.

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?

Two sentences, front-loaded with the resource and its fields, then the usage instruction. Dense but every clause carries information; the parenthetical definition of 'indexed' is justified because the term is otherwise ambiguous.

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 carries the burden of return values and it does so by enumerating the record fields. Missing only minor operational detail such as result ordering or whether the empty-ids case is bounded — small gaps for a two-parameter read tool.

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 baseline is 3, but the description adds meaning the schema does not: it tells the agent that the ids come from a statement's sources list, which is the essential discovery path for that parameter. The company parameter is left to the schema ('company id from search_companies'), which already covers it.

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+resource: retrieves the source documents of a company's latest snapshot, and enumerates exactly what each record contains (kind, period, date, URL, SHA-256). The verb 'get' plus the scope 'latest snapshot' separates it from get_statement and get_snapshot_info, though no sibling is named outright.

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?

'Pass the document ids found in a statement's sources to resolve them' gives a concrete workflow: use this after reading a statement's sources list to resolve document ids. 'Leave empty for all' (in the schema) implies the browse-all case. It stops short of explicit when-not-to-use or naming get_statement directly.

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