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

Beyond the annotations, the description reveals that results are pre-computed matches, enumerates the returned fields (reasons, blockers, why_now, comparables, score, confidence, computed date), and gives the critical NOT_COVERED caveat that absence of scores is not a claim that nothing fits. This adds real behavioral context and prevents an agent from overinterpreting the sentinel.

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?

The description is compact and front-loaded: the first sentence states action, scope, and return content, and the second sentence clarifies a semantically important sentinel. Every sentence earns its place with no 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 successfully carries the burden of explaining return values: it lists the per-company fields and the NOT_COVERED sentinel. It also identifies the required identifier type. It could mention ordering or default limit behavior, but those are minor given the schema already covers the limit bounds.

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 input schema already documents dfx_id's format and domain, and limit's bounds and default. The description reinforces the dfx:pe form but does not add meaningful semantics for limit, such as ordering or pagination behavior. Since schema coverage is partial and the description compensates only slightly, a mid-range score is appropriate.

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?

The description opens with a specific verb and resource: 'Computed company_for_buyer matches for one private equity firm.' It clearly distinguishes this tool from inverse or sibling tools like find_pe_buyers_for_company by stating it returns companies for a buyer, and it names the required identifier domain (dfx:pe: id).

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?

The description clearly scopes the tool to one private equity firm and explains the NOT_COVERED condition, which is important for interpreting empty or absent scores. It does not explicitly name alternatives or state when not to use this tool, but the scope is clear enough for selection.

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