Set an agent's skills

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

Annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the real behavioral load and does so: it explains the destructive replace semantics, the empty-list case, duplicate handling, the 404 failure mode, and the managed-agent restriction. That is substantially more than the annotations convey.

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 tight sentences, front-loaded with the replace semantics before the constraints and error behavior. 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?

For a mutation tool with no output schema and only minimal annotations, the description covers effects, error behavior, and eligibility constraints well. It stops short of indicating what the call returns or whether the operation is idempotent/atomic.

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 67% (agent_id and the account-id header are documented in-schema), and the description adds genuine constraint semantics for skillId — workspace/Orchestra membership, 404 refusal, duplicate tolerance — that the schema's bare uuid4 type does not express. The body's array and agent_id parameters get no extra description, keeping this below a 5.

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 opening clause states a specific verb (replace) plus resource (agent's skills) and defines the replacement scope precisely: omitted skills are detached, empty list detaches all. This is unmistakably distinct from list_agent_skills and set_agent_integrations among the siblings.

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?

It gives clear conditions for correct use (skills must belong to the same workspace or be Orchestra-managed; 404 on violation; duplicates ignored) and a hard exclusion (Orchestra-managed agents cannot be changed). It does not, however, name the sibling to use when you only want to add rather than replace, so routing to alternatives is left to inference.

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