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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context beyond annotations: it explains the default behavior of the 'filing_types' filter (omit for main reports only, excludes ad-hoc), and describes the exact return structure (summary + table up to 50 filings). It also mentions the need to pass [] for all indexed types or an allowlist. It doesn't mention pagination limits beyond 50, but that is explicit in the return. Strong supplemental context.

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 well-structured: it starts with the primary purpose, then the alternative, then the behavior, and ends with filter details. It is dense but every sentence earns its place. The formatting with line breaks for returns and filter details improves readability. It is concise given the complexity it covers.

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?

Given the tool's moderate complexity (2 params, no output schema), the description is complete for effective invocation. It doesn't need to explain return values because it explicitly lists the summary fields and table columns. It covers the nuanced filing_types behavior thoroughly, which is the main source of confusion. Annotations cover mutability. No gaps that would prevent correct use.

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 baseline 3. However, the description adds significant meaning beyond the schema: it explains the default behavior of filing_types in detail (what types are included/excluded) and instructs to pass [] for all indexed types or an explicit allowlist. It also clarifies the purpose of the return values (summary + table). This goes beyond the schema's straightforward parameter descriptions, enriching the agent's understanding of how to use the filter.

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 is very specific about its purpose: discovering which SEC filings exist for a ticker before searching content. It clearly states the resource (SEC filings for a ticker) and the action (list). Sibling differentiation is excellent: it explicitly contrasts with 'filing_search' for content, and other siblings like 'list_tables' or 'run_sql' are clearly different. The summary header and return table are described.

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 explicit guidance on when to use this tool: 'to discover which SEC filings exist... before searching content'. It also explicitly states when to use the alternative: 'For the actual content use filing_search instead.' This is a clear when/when-not with named alternative. No further exclusions needed.

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