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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description goes well beyond them with a detailed entitlement/paywall model: 5-row full lists with locked counts, per-record truncation to 3 related names, contact values and decision-maker names never returned, and the `entitlement`/`locked` disclosures. This is exactly the kind of behavioral context annotations cannot carry.

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 purpose is front-loaded in the first clause, and each subsequent block (result fields, NOT_COVERED, ACCESS) earns its place. The dense access sentence is long but information-dense rather than padded.

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 fully carries the burden of describing return values, including the matcher fields, the entitlement/locked envelope, and truncation behavior. Nothing an agent needs to interpret or call the tool correctly 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 50%: dfx_id is documented in the schema, while `limit` is not. The description reinforces dfx_id's origin and format ('a dfx:pe: company id from search_pe_platforms') and hints at list-vs-record behavior, but adds nothing about the limit parameter or pagination. Baseline 3 is appropriate at this coverage level.

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 states a specific verb and resource ('Computed addon_for_platform matches for one platform') and enumerates the returned fields (reasons, blockers, why_now, comparable add-ons, owner, score, confidence, computed date), so the agent knows exactly what it produces. It also names search_pe_platforms as the source of the required id. It stops short of explicitly distinguishing itself from the reverse-direction siblings (find_pe_buyers_for_company, find_pe_companies_for_buyer).

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?

Usage is implied: call it with a dfx:pe id from search_pe_platforms to get add-on candidates. It clarifies the NOT_COVERED case ('not a statement that no add-on fits'), which prevents misreading an empty result. However, it never states when to prefer this over alternatives or any exclusions.

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