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

Annotations only cover the safety profile (read-only, idempotent, non-destructive), so the description carries the burden of behavioral disclosure — and it delivers. It discloses a specific error code (404 OWNERSHIP_SECURITY_NOT_FOUND), credit costs per mode (30 flat / 40 grouped) and that a 404 is still charged, multi-CUSIP ticker matching, and the unpaged behavior of grouped mode. This is exceptional context beyond what annotations provide.

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?

The description is front-loaded with purpose and anchoring constraints, and each sentence carries real information: error behavior, securities block contents, output modes, pricing, and sibling relation. It runs slightly long and ends with noise — the raw 'POST /api/v1/...' endpoint, a doc-file reference, and an ambiguous trailing sentence ('The URL opens the filing's EDGAR index page...') whose antecedent is unclear. Minor clutter in an otherwise dense, well-structured definition.

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 10-parameter, dual-mode tool with no output schema, the description is remarkably complete: input anchoring, unknown-security error, credit costs, pagination differences between modes, output shape for both modes, and the relationship to get_institutional_portfolio are all covered. The few gaps — per-row column details delegated to the sibling's schema and no routing guidance versus search_institutional_holdings — are minor relative to the tool's complexity.

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 baseline of 3 applies; the tool description largely paraphrases the schema ('anchored by exactly one of cusip / ticker', group_by_quarter returning 'holders, total_shares, total_value over live stock rows — unpaged'). Its modest added value is organizing which parameters narrow flat mode (quarter, type, activity, sort_by) versus which switch modes, but it introduces no genuinely new per-parameter meaning.

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?

The description opens with a precise verb-resource-scope statement: 'One security's 13F holder rows across managers, anchored by exactly one of cusip / ticker.' It explicitly differentiates from the sibling get_institutional_portfolio ('returns the same detail rows as get_institutional_portfolio with manager_cik / manager_name added'), so an agent can tell these apart without opening schemas. The title and description agree, and the security-anchoring constraint is front and center.

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?

Clear context is established: this is the security-anchored counterpart to the manager-anchored get_institutional_portfolio, and the two output modes (flat detail vs grouped aggregates) are explained with their narrowing parameters. What's missing is an explicit exclusion — e.g., no guidance on when the sibling search_institutional_holdings would be the better choice for cross-security or text-based searches. It names the relationship but stops short of full when-not-to-use routing.

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