update_agent

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the mutation/idempotency profile is covered. The description adds a genuinely non-derivable constraint — the call requires an org-level key and agent-scoped keys cannot mutate agents — which prevents a whole class of failed calls. It does not say whether omitted fields are preserved or how partial updates behave.

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?

Two sentences, no filler, with the action and its target front-loaded before the operational constraint. The field enumeration partly duplicates the schema but reads quickly and aids scanning.

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 partial-update mutation with full annotation coverage and no output schema, the description covers purpose and the key auth gate. It leaves minor but real gaps: whether unspecified fields are preserved, and what happens on validation/permission failure.

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 100% and every parameter (name, status enum, agent_id, metadata 16KB limit, description-null-clears) is already documented in the schema, so the baseline of 3 applies. The description restates the field set but adds no format, null-semantics, or update-mode detail beyond the schema.

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 gives a specific verb (Update) plus the resource (an agent) and enumerates the mutable fields (name, description, metadata, status), which separates it from read-only siblings like get_agent and from create_agent/delete_agent. It stops short of explicitly naming those siblings or stating what it is not, so it is clear but not fully differentiated.

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?

Usage is implied by the auth prerequisite: 'Requires an org-level API key — agent-scoped keys cannot mutate agents.' That tells the caller when the call will succeed, but there is no explicit when-to-use-vs-alternative guidance (e.g., use create_agent first, use delete_agent to remove, or that this is a partial update).

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