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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world). The description adds the operationally critical facts an agent cannot get elsewhere: two parameters are locked and cannot be overridden, there is no offset, results are tier-gated with a 403 on Free, and email visibility is redacted on Pro Lite but full on Pro. It also discloses the return fields (tech stack, RDAP registration date, has_known_emails) with no output schema present.

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?

Well front-loaded: purpose and locked parameters come before the return description and the tier caveats. The 'Inputs: ...' enumeration, however, repeats schema descriptions almost verbatim and is the one block that does not fully earn its space.

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 7-parameter, output-schema-less tool, everything an agent needs is present: what is returned, that the tool is a filtered view of search_startups, how to paginate past it, the auth/tier requirement, and the sibling tools that complete the workflow.

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 already 100%, so the baseline is 3, but the description adds meaning the schema cannot express (the fixed stealth/sort behavior and the no-offset constraint). The per-parameter restatement largely duplicates schema text (defaults, TLD list, with_emails consequence), so it does not fully earn 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?

Opens with a precise framing: a 'convenience wrapper around search_startups pre-tuned for fresh-stealth deal-flow,' immediately telling the agent both the verb/resource and the exact relationship to the sibling it wraps. It then states the two hard-coded parameters (stealth=true, sort=founded_date.desc) that differentiate this tool from search_startups.

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?

Explicit routing: 'There is no offset; use search_startups with stealth=true to page further' names the alternative and the condition that selects it. It also prescribes a workflow ('Combine with list_startup_team and discover_email to surface the actual addresses') and states the tier gate (Pro Lite+, Free tier 403s) that determines whether the call is even usable.

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