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

Annotations already declare a read-only, non-destructive, non-open-world operation, and the description stays consistent while adding real context: the fit logic is 'experimental' and uses 'public, company-level signals only,' and the sector filter is 'strict.' Those caveats materially change how an agent should interpret and present results. It does not discuss result caps beyond limit=10 or latency/pagination, but no output schema exists so the 'reason for each' note partly covers returns.

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 and nearly every clause carries operational information (defaults, strictness, opt-in routing). The middle sentence is dense and parenthetical-heavy ('innovation or pilot desks, dated startup purchases, supplier intake, readiness'), which slows parsing, but no sentence is filler.

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 5-parameter, all-optional, read-only discovery tool with no output schema, the description covers intent, defaults, buyer-type routing, and interpretation caveats. Minor gaps remain: it never says what happens when no company or what_you_sell is provided, and 'if listed' is an unexplained conditional.

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 80%, so the baseline is 3, and the description earns above that by adding behavior the schema does not convey: sector filtering is strict, hospital/university buyers surface only via sector or buyer_type, buyer_type=startup targets SalesBook companies, and company is optional if what_you_sell is supplied. These mappings clarify the interaction between parameters rather than restating their definitions.

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 concrete verb and resource ('the 10 best-fit buyers for a company, with the reason for each') plus the intended caller ('For startups looking for customers'), which immediately separates it from siblings such as search_startups or find_alternatives. Default ranking basis and default buyer population are spelled out, so an agent knows exactly what it will get back.

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 triggering context (startups looking for customers) and explicit routing to a sibling: 'To be considered for an introduction, use opt_in_for_intros.' It also states when hospital systems and universities appear ('only when you ask') versus the default enterprise set. It stops short of distinguishing this from other lookup siblings like find_alternatives or compare_vendors.

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