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

Annotations only declare read-only/idempotent safety. The description goes well beyond: it discloses free-plan truncation (first 5 rows, locked.count/locked.by_type), that contact values and decision-maker names are never returned, and that every answer self-reports withholding in `entitlement` and `locked`.

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-loads what the tool returns, then the NOT_COVERED semantics, then access limits. Dense but every clause carries information, except the trailing promotional line about a free trial, which is sales copy rather than tool guidance.

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-shape burden and does so thoroughly (reasons, blockers, why_now, comparables, deal partner, score, confidence, model version, computed date). Entitlement behavior and the NOT_COVERED edge case are both covered, leaving no material gap for correct invocation.

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?

Only dfx_id is documented in the schema, and the description merely restates its id prefixes without adding format or validation detail. The `limit` parameter (default 20, max 50) is undocumented in both the schema and the description, so the description fails to compensate for the 50% coverage gap.

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+resource+scope: computed buyer_for_company matches from the PE matcher for a single company id, and enumerates what each row contains. It is clearly distinguishable from the inverse sibling find_pe_companies_for_buyer and from the broader find_capital_for_opportunity.

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?

Explicitly routes adjacent use cases elsewhere ('For sponsors, family offices and capital providers as well, use find_capital_for_opportunity') and explains the negative-result case (NOT_COVERED means DFX hasn't computed, never that no buyer exists), which prevents a serious misread.

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