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

Beyond the readOnly/idempotent annotations it adds real behavior: a pre-schema state returns available=false, the exact payload fields per proposal are enumerated, and a prompt-injection warning marks names and message text as untrusted. These are facts an agent cannot get from annotations or schema.

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 the purpose, then the payload fields, then the safety constraints — a sensible order. It is dense and mostly earns its space, though the mid-sentence field list (link_version, human_locked, tombstone_id) is heavy for a description and reads like schema content.

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?

An output schema exists so return values need not be explained, and the description still covers the empty-state, the read-only conflict rule, and the untrusted-content caveat. Nothing an agent needs to call this safely or interpret it 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 100% and the sole cursor parameter is already documented as an opaque cursor from a previous page, so the description adds no parameter detail. Baseline 3 applies; pagination is only hinted at by the word 'waiting' rather than explained.

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 (identity decisions awaiting a person) and enumerates the two result kinds — link proposals and conflicts — with their distinguishing fields. Adjacent siblings such as list_identity_candidates and list_identity_changes are implicitly differentiated by the 'waiting for a person' framing.

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 tells the agent that conflicts must be shown but never resolved, and that proposals are for a human to accept or dismiss. It does not, however, name which sibling to call for candidate matching or for the resolution action itself, so routing around the identity tool family is only partially covered.

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