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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful behavioral fact beyond that: rubric text, rules, and evaluator URLs are write-only and never echoed in output, which prevents the agent from expecting those 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?

Three compact clauses, front-loaded with the list verb and field set, followed by the write-only caveat and the management routing. Every clause carries information; there is no filler.

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-value explanation is not strictly required, yet the description still summarizes key fields and the crucial write-only caveat. Combined with the sibling routing, an agent has everything needed to call and interpret this tool.

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?

There are zero input parameters, so the baseline is 4. The description instead documents output fields (tier enum, phase, floor, referenceMediaIds), which is useful though technically beyond input semantics.

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 registered critics") and enumerates the returned fields (criticId, label, tier, phase, floor, referenceMediaIds). It is clearly distinguishable from the sibling management tools register_critic and delete_critic, which are named directly.

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?

The description routes write operations to register_critic (upsert) and delete_critic, giving the agent clear context for the read/write split. It does not state an explicit when-to-use trigger for listing itself, but for a zero-arg list tool the implied usage is unambiguous.

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