search_filings

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety burden is lifted. The description adds real value beyond them: the retrieval is lexical BM25 rather than semantic, results are chunked passages carrying chunk_id, and answers must cite via [chunk_id], which shapes how the agent must consume output.

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?

Three short sentences, each doing distinct work: what it searches, what it returns, how to cite, and a query-language tip. Front-loaded with zero filler.

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 detail is not needed, and the citation convention is a useful addition. However, with four parameters at 0% schema coverage and no definition of what 'latest' means (how many filings back, whether it spans all tickers), the definition is not complete enough for confident invocation.

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%, so the description carries the full burden, and it only covers 'query' (recommend English). The k, form, and ticker parameters are left entirely unexplained beyond bare titles and defaults; an agent cannot tell whether form takes '10-K' or '10-K/Q' or what ticker filtering does to the 'latest' scope.

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 mechanism (BM25 retrieval) over a specific resource (latest 10-K/10-Q source text) and declares the return shape (paragraphs with chunk_id). No sibling is named, but the resource is distinct enough from get_quote/get_price_history/get_company_news that an agent can route correctly.

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?

Scope is implied by 'latest 10-K/10-Q', so the agent knows roughly when this applies, and it gives a language recommendation for the query. But it never states when to prefer this over get_key_financials or get_company_news, and gives no exclusions or preconditions.

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