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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true. The description adds real value beyond them: hard limits of 200 KB and 500 people, the fact that nothing changes in the role, that a re-sent file returns the same import, and that paid analyses may be triggered. However it doesn't cover permissions/auth needs or how the preview is returned, so against a low annotation bar this is solid but not exhaustive.

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 core action and the non-mutating guarantee lead, and every sentence carries information (limits, preview contents, idempotency). It is dense in semicolons and parentheticals, which slightly slows parsing, but there is no filler to cut.

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, the description fully accounts for the return: readiness categories, rows already in the role, excluded lines with reasons, and candidate paid analyses. Combined with size limits, idempotency and the follow-up call, an agent has everything needed to invoke it and interpret the result.

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 coverage is 67%, with text and filename already documented there. The description compensates for the gap by detailing the accepted content — GitHub handles, github.com links, LinkedIn /in/ links, optional columns github/linkedin/name/note — and clarifying that names never identify anyone. role_id remains undocumented in both places, keeping it below a 5.

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 — bringing a list of people into a role — and immediately scopes it to file content rather than direct adds, which separates it from add_people_to_role and run_import. The tool's effective contract (preview that changes nothing) is stated up front, so an agent can distinguish it from siblings 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?

Gives an explicit workflow: call this, show the preview to the user, then call run_import. It also names resolve_import_row as the path for uncertain LinkedIn rows and says those rows are never added or scored, which is clear when-not guidance. Alternatives and sequencing are both spelled out.

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