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

Annotations already carry the read-only/idempotent/non-destructive profile, and the description adds substantial behavior beyond that: case-insensitive matching, quoted-phrase exact matching, AND semantics ('every word of the query'), best-first ranking, the ranked most-mentioned-sections list, full passage text with section and subsection, and default coverage of all three documents.

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 clause and the return shape follows immediately; every sentence carries information. The trailing example list is long (seven examples) and slightly dilutes an otherwise tight, well-ordered paragraph.

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?

With no output schema, the description carries the full burden of describing returns and does so completely: passages in full with section/subsection, ranking order, and the ranked section list. An agent has everything needed to call it and interpret results.

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 the schema already documents ticker, query, record, limit and documents, including defaults and bounds. The description restates the document categories and query syntax rather than adding new semantics, so the baseline of 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?

Specific verb ('Find') plus resource ('what a company's filings say'), immediately scoped to a keyword search across three named document sets. It is clearly distinguishable from get_narrative/get_events, which it positions as the follow-up readers for whole sections.

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?

It states the search context (keyword lookup across filings) and explicitly routes the agent onward to get_narrative or get_events to read a matched section whole, plus list_periods for record discovery. It never states when this tool is the wrong choice (e.g., vs. get_filings for raw documents), so it falls short of full when/when-not coverage.

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