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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers real behavior on top: the fallback to candidate lists on ambiguous names, the always-included sections (company profile, weighted indication), and the unlock status / AI summary presence in reports. That is more than the annotations provide and directly shapes how an agent should react to the response.

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?

Front-loaded with purpose and the key lookup rule; every clause maps to something an agent needs (contents, fallback, filtering). The first sentence is a long enumeration that a bulleted listing would have made scannable, 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?

With no output schema, the description carries the return-value burden and does so thoroughly, and all three parameters are covered by a 100%-documented schema. Nothing an agent needs to call this correctly — inputs, filtering semantics, ambiguity handling — is missing.

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 100%, so baseline is 3; the description still adds value by clarifying that sections filtering is partial — company profile and weighted indication are always returned regardless of the filter — and by explaining the name-match fallback that makes the valuation id parameter meaningful. It does not restate the parameter formats, but the schema already does.

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 specific verb+resource ("Returns one valuation") and enumerates exactly what that valuation contains (methods, ranges, DLOM, weighted indication, assumptions, reports). It never names or differentiates itself from siblings like get_company_financials or list_companies, so an agent must infer the split from the returned-data list alone.

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?

Clear about the calling condition ("chosen by company name") and handles the ambiguous case explicitly — "If several valuations match the name, returns the candidates instead" — plus guidance to use "sections" to limit the answer. It stops short of stating when to prefer this over list_companies or get_company_financials.

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