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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), and the description adds genuine behavioral value: each item carries a handle that generate tools accept unmodified, supplying both face and description. Pagination/ordering behavior is not discussed, which keeps this from a 5.

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?

Four short sentences, logically ordered: what a subject is, why the handle matters, when to check it, and how tags filter. Dense but every sentence carries information; the definition is front-loaded.

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 shape need not be explained, and annotations cover safety. With zero required parameters an agent can call this safely, and the description supplies the identity/handle concept that motivates the call; only ordering/limit defaults and paging remain unaddressed.

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 only 14% (7 params, essentially only `cursor` documented in the schema), so the description needs to compensate and largely does not. It adds real semantics for just one parameter — `tags` filters to subjects carrying every tag named (AND, not OR) — while `q`, `kind`, `limit`, `order`, and `favorite` remain unexplained.

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 concretely defines the resource as 'the named identities this account reuses' and enumerates the kinds (character, location, product, prop, wardrobe), which matches the `kind` enum. The list verb is implied by the name/title rather than stated outright, but an agent can tell this apart from create_subject/delete_subject/update_subject.

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?

States the intended workflow explicitly: check this before list_media, and pass the returned `subject` handle as-is to the generate tools so the identity's face and description come along. It gives clear context for use but does not name alternative tools for related tasks or state when NOT to use it.

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