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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description goes far beyond these by explaining critical interpretation rules: null severity means found but not assessed, name_unverified may indicate a different company, and empty results are not statements about never-searched subjects. These are essential behavioral details that prevent misreporting and are not captured in structured fields.

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 moderately long with a clear structure: a concise opening sentence, a historical anecdote that provides context, then two highlighted warnings, and a final note. The warnings are appropriately emphasized, but the historical paragraph adds length without direct operational value. It is not overly verbose, but it could be more concise while retaining the critical warnings.

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 read-only tool with two simple params and no output schema, the description covers the most critical interpretation nuances (null severity, name_unverified, empty results). It also mentions fields like severity and match_confidence, giving some output semantics. It lacks explicit mention of pagination or the exact output structure, but given the tool's safety profile and the richness of behavioral guidance, it is reasonably complete for an agent to call correctly.

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?

The schema has 0% description coverage for the two parameters (limit, symbol). The description does not mention either parameter, leaving the agent to infer their meaning from names and defaults. Symbol is likely a ticker, but the description doesn't clarify its role in filtering issuers, nor does it explain the limit behavior. Since schema coverage is zero, the description should compensate, but it adds no parameter semantics.

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 states the tool retrieves public-record documents (SEC filings and federal court dockets) about tracked issuers. This is a clear verb+resource statement. It doesn't explicitly contrast with siblings like get_asset_fundamentals, but the focus on public records and dockets is distinct enough. The title 'Public disclosures' reinforces the purpose.

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?

The description provides rich context about why the tool exists (RWA failures) and how to interpret results, but it does not explicitly state when to use this tool versus alternatives. There is no 'use this instead of X' guidance, and no mention of prerequisites or conditions that would select this tool over other get_* tools. The usage is implied by the tool's purpose but not directly stated.

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