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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new operational context: cost ('1 db credit'), a hard return cap ('up to 100 per call'), offset pagination, an account requirement, and that paid plans change which fields come back. It stops short of describing result ordering behavior or the empty-result note in any depth.

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?

A single dense paragraph with no filler; purpose leads, then filters, then return shape, then example, then limits and pairing. It is longer than average but every sentence carries information for a 63-parameter tool. Slightly front-loaded toward enumeration rather than routing, keeping it just under top marks.

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 63-parameter, zero-required tool with no output schema, the description covers what is missing elsewhere: the shape of each result (latest round, sectors, HQ, founded date, score), the plan-dependent field differences, the 100-per-call cap with offset paging, credit cost, and account prerequisite. An agent has everything needed to call it correctly without opening the schema.

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 the baseline is 3 and the schema carries the per-parameter burden. The description still adds value by grouping the 63 filters into recognizable categories (sector, geography, funding, scores, tech stack, stealth) and demonstrating how several combine in one query, which helps an agent plan a call rather than read 63 fields in isolation.

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 ('Search the startup database') and enumerates the full filter surface plus the returned fields, so an agent knows exactly what the tool does. It also signals its position relative to siblings by noting it pairs with list_startup_team and discover_email, distinguishing it from the get_startup/enrich_company retrieval tools.

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 clear usage context ('with any combination of filters'), a concrete worked example (round_series=Seed, raised_after=..., sort=last_round_date.desc), and the downstream composition path with list_startup_team and discover_email. However it never states when NOT to use this tool or named alternatives (e.g. find_stealth_startups, generate_startup_list), so exclusions are absent.

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