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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety bar is pre-met; the description adds real behavioral context on top: it returns ambiguity and insufficient-evidence states, sameAs candidates are unapproved, Google crosscheck is disabled remotely, and public prose/aliases/external links/media are withheld. These are non-obvious outcome and withholding behaviors an agent could not infer from structured fields.

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, which is good, but the remainder is a seven-sentence wall of compressed jargon ('bounded direct-record admission without recursive content certification') whose clauses are hard to parse and unevenly weighted relative to their importance to an agent.

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 does some of the return-value work (ambiguity, insufficient-evidence states, withheld fields), but the required nested 'envelope' parameter is entirely unspecified and the dense internal terminology leaves an agent unsure what to pass or what a successful result looks like.

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 description coverage is 0%, so the description carries the burden and only partially delivers: it covers max_candidates ('Default 3, maximum 5'), gestures at google_crosscheck ('disabled remotely'), and implies the envelope is local evidence, but says nothing about refresh and gives no format for the envelope object despite it being the sole required nested parameter.

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 and resource: 'Canonical discovery of one identity from a local evidence envelope', which tells the agent this returns a single identity rather than a list. However, the vocabulary ('canonical', 'evidence envelope') is obscure and the description never distinguishes this from siblings like kg_resolve or kg_lookup_entities, so sibling differentiation rests on the name 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?

There is no statement of when to use this tool versus kg_resolve, kg_lookup_entities, kg_search, or kg_entity, all of which plausibly overlap with identity discovery. The only directive content (default 3, maximum 5 candidates) is a parameter constraint, not usage guidance.

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