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

Adds real behavior beyond annotations: two-day reply SLA, delivery to the calling user's email, the unauthenticated caller's obligation to pass email, and a shared hourly limit with send_feedback that produces a tool error when exceeded. It does not explain whether requests persist, whether duplicate briefs are deduplicated, or what the reply contains beyond the address.

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?

Purpose is front-loaded, followed by delivery mechanics and the rate limit. Sentences are dense but each carries non-redundant information; the email conditional is wordy and takes a moment to parse.

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 mutation tool with no output schema, the description covers purpose, delivery target, auth-dependent email requirement, throttling, and the return value ('returns the address the reply goes to'). The unexplained threadId parameter is the main residual gap.

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 description clarifies the brief, the filters, and the conditional role of email for credential-less callers. With schema coverage at 50% and detailed nested filter descriptions in the schema, this is a baseline 3; threadId is never explained in the description.

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+resource: asks the Starcovery team to hand-pick creators for a brief and its filters. It implies a human-mediated request versus automated search, but does not name search_creators or another sibling explicitly.

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?

No explicit when-to-use or when-not-to-use guidance versus siblings such as search_creators or generate_campaign_matches. The only routing hint is the schema note 'threadId from thread_turn, when one holds the search', which is buried and inferred rather than stated.

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