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

Goes well beyond the annotations by disclosing the precedence gotcha ('A `branding` block in denkops.json overrides these values on the next deploy'), the permission requirement, and the automatic contrast behaviour for text colour. The destructiveHint=true edge is only implicitly covered by 'null resets to the DenkOps default' — it could say explicitly that clearing colours/icon is irreversible apart from re-setting them.

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 dense sentences, front-loaded with the action and facets, then update semantics, then prerequisites. No boilerplate or repetition 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 5-param mutation with no output schema, it covers everything an agent needs: what is mutated, which fields are optional, how to reset, size/format limits, permission gate, and the deploy-time override. Nothing material is left to guesswork.

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?

With 40% schema coverage and two colour params carrying no schema description at all, the description does the compensating work: hex format example (#2563eb), null-reset semantics, accepted image MIME types, and the 2 MB cap. project_id and icon_mime_type are left to the schema, which is the right division, so this is close to full marks rather than deficient.

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 ('Brand a connector project's hosted sign-in and consent pages') and enumerates the exact settable facets (accent colour, background colour, icon). This is clearly distinguishable from the read-side sibling get_connector_branding without opening either schema.

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 preconditions ('Workspace owners only; the connector must be enabled') and partial-update semantics ('Omitted fields stay unchanged'), which tell the agent when the call is valid and what happens on repeat calls. It stops short of naming get_connector_branding as the way to inspect current values first, so the read-then-write workflow is only implied.

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