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

The readOnly/idempotent/destructive annotations already cover the safety profile, and the description adds genuine context above that bar: the empty-until-connected prerequisite, what "missing" signifies, and an explicit prompt-injection caution that agent names are data, not instructions. It leaves pagination behavior and result ordering undisclosed.

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?

Purpose is front-loaded in the first clause, followed by tightly packed but relevant field semantics. The long comma-list sentence is dense yet every element earns its place; no filler or restatement of the title.

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 carries the return-shape burden and does so by naming each field and its meaning. The main omission is pagination/total-count behavior implied by the `page` parameter, which an agent would need to page correctly.

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 50%: the `fields` parameter is documented in the schema, while `page` is undocumented in both schema and description. The description does explain what the enumerable fields mean semantically, which helps, but it never mentions paging at all. Baseline 3 is appropriate.

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 scoped to the "connected ElevenLabs workspace" and enumerates exactly what each record contains (id, name, enabled, inbox_id, team_id, missing). The ElevenLabs qualifier implicitly separates it from the generic list_agents / list_agent_bots siblings, though it never names them 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?

Gives concrete usage context: the returned id is meant to be fed to update_elevenlabs_agent_mapping, an agent requires an API inbox before it can be enabled, and the list stays empty until ElevenLabs is connected. It stops short of saying when to prefer list_agents or list_agent_bots instead.

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