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

Annotations only declare readOnlyHint=true; the description adds substantial behavior: returned text is untrusted evidence and never instructions (prompt-injection guard), the backtest constraint that asOf must not exceed the simulated timestamp, and visible-failure semantics for unsupported history. None of that is inferable from the annotation or schema.

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 purpose and id contract, then constraints and failure behavior in descending priority; no filler sentences. It is dense and jargon-heavy (accessionNumber, intraday replay, original-vintage) and repeats the section-alias list already in the schema, costing some tightness.

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?

For a 4-parameter, read-only fetch with full schema coverage and no output schema, the definition covers id provenance, optional sectioning, historical-point-in-time semantics, failure modes, and trust handling of returned text. An agent has everything needed to call it correctly and to interpret what comes back.

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 real meaning beyond the schema: the backtest rule for asOf ('must not exceed the exact simulated timestamp') and the enumeration of section aliases in the body text. It largely restates the documentId format already documented in the schema, which keeps it from a 5.

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 and resource ('Retrieve a public document by id') plus the initial dataset scope ('SEC filing documents from EDGAR'). It routes the agent to sibling tools (search_documents, query_data) for how ids are produced, so it is distinguishable from those siblings without opening a schema.

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 concrete preconditions ('Use ids returned by search_documents, query_data sec.full_text_search, or query_data sec.filing_exhibits') and the id contract for SEC ('CIK:accessionNumber[:filename]'). It also names invalid conditions ('date-only legacy SEC filtering is not qualified intraday replay; unsupported original-history requests fail visibly'), but never states a clean 'do not use this tool when X' alternative for non-document lookups.

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