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

Annotations already cover read-only, idempotent, open-world behavior, and the description adds genuine non-obvious context: the window is applied to the transaction date rather than the filing date, so results can precede the latest filing. It omits return/ordering behavior, but the annotation plus this semantic note gives solid behavioral grounding.

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?

Two short sentences, front-loaded with the core purpose, with the second sentence delivering the one non-obvious semantic caveat. No filler or repetition.

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 four-parameter, fully-schema-documented, non-paginated tool with no output schema, the description covers the aggregation concept and the key date-field caveat. It could say a bit more about what a result row contains (e.g. company, insider count) or default limit behavior, but nothing essential for correct invocation 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 limit, roles, window, and min_insiders are already documented, including the 'not paginated' constraint and the 7d example. The description only slightly deepens the window parameter ('transaction date, not the filing date'), which the schema already touches on, so baseline 3 applies.

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 resource ('Finds companies where several distinct insiders bought') and defines the aggregation scope ('several distinct insiders'), which separates it from sibling listing tools like insider_list_transactions and insider_list_recent that return raw transaction rows rather than clustered companies.

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 useful context on how the window applies ('transaction date, not the filing date'), which implies when the signal is meaningful, but never states when to prefer this over insider_list_transactions or insider_list_recent, nor any exclusions. Usage is inferable rather than explicit.

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