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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavior: results are private identities, filtering is exact-match, pagination must reuse the same filter, and duplicate names require user disambiguation. It does not describe the shape of a returned identity, which is the main remaining gap.

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?

Core listing and filtering behavior is front-loaded in the first two sentences, with follow-up routing after. Every sentence carries a directive, but the two trailing sentences about characterBuilderUrl and Character Builder drift into workflow narration that could be trimmed without losing selectability.

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?

There is no output schema, so the description bears responsibility for describing what a returned identity looks like, and it does not — no mention of identifiers, names, look fields, or where characterBuilderUrl comes from. For a list tool with pagination and a disambiguation rule, this is adequate but leaves the agent guessing about the response it will receive.

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 0%, so the description must carry the meaning of both parameters, and it largely does: name is an exact-Match filter (not a fuzzy search) and cursor continues the listing under the same filter. Minor friction remains because the description calls the cursor "nextCursor" while the parameter is named "cursor", and it never says cursors are opaque numeric tokens or that omitting both returns the first page.

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 ("List private identities saved in Character Studio") and immediately distinguishes itself from get_saved_character and save_character by naming both siblings and their roles. An agent can tell what this tool does and what it does not do from the first sentence.

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 the agent: use get_saved_character to pick a look, save_character to persist a new one, and ask the user when multiple names match. These are clear when-to-use and next-step rules. The only weakness is the reference to "characterBuilderUrl" and "Character Builder" with no stated way to obtain that URL, which leaves part of the routing advice unactionable.

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