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

Annotations cover only the safety profile (readOnly/destructive/openWorld), but the description goes far beyond: ticker search surfaces retired-symbol rows, rows gain current_ticker, share classes are not merged, retired symbols return only their own rows, plus source (SEC bulk dataset insider_filings_v2), coverage (2006→present), and refresh cadence (quarterly). This is rich behavioral disclosure the annotations cannot supply.

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?

Information-dense with almost no filler, but it front-loads ticker/retired-symbol edge cases before stating the core purpose, which is buried mid-paragraph. A reader has to get past the caveats to learn what the tool returns; a short purpose lead would improve ordering.

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 and 12 optional parameters, the description compensates by enumerating the returned row fields (company_cik, company_name, ticker, document_type, filing_date, period_of_report, is_amendment, reporting_owners[], signature rows, per-table counts), the data provenance, and the join keys to siblings. Nothing an agent needs to call it correctly is missing.

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 per-parameter docs already carry the baseline. The description still adds value with concrete filter-combo recipes (ticker+document_type, company_cik+is_amendment, accession_number alone, ticker+reporting_owner_name) and clarifies that document_type uses raw SEC form codes including /A amendments. It stops short of full combinatorial guidance, but exceeds the 100%-coverage baseline.

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: 'Returns FILING-LEVEL records from SEC Form 3/4/5 filings — one row per filing (accession).' It explicitly positions itself as the filing INDEX and names the two siblings it is not (get_insider_transactions for trades, get_insider_holdings for positions). An agent can distinguish it from every neighbor 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?

Provides an explicit when-to-use list ('list an issuer's insider filings, find a specific accession, filter by form type... count filings over a period, or size a filing') and names the alternatives with the join key ('They join on accession_number'). This is textbook when/when-not/alternatives routing.

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