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

Adds substantial context beyond the annotations: the customer-facing page behavior (message shown with a dashboard button), that staffSummary is stored in the support log and never shown to the customer, and that unanswered items persist as a to-do. The 'call once' instruction aligns with idempotentHint=false, reinforcing non-repeatable behavior.

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?

Front-loads the audience restriction and core action, then covers the customer page effect and the timing condition. It is dense and the parenthetical clauses make it slightly meandering, but every sentence carries usable information.

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, the description explains the downstream effects an agent cannot otherwise infer: the message is displayed to the customer with a dashboard button, the staff summary goes only to the support log, and unaddressed items remain as to-dos. Combined with annotations and full param docs, nothing essential is missing.

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 100%, so all three parameters are already fully documented in the schema. The description only reinforces this by mentioning 'Pass staffSummary for support' and the language requirement for the message, adding marginal meaning beyond the schema. 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: 'Mark your work on the onboarding as done and give the customer your closing message.' Combined with the 'STAFF ONLY' restriction and the distinction from siblings like start_agent_onboarding_build and complete_onboarding, an agent can identify what this tool does without opening the 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 explicit when-to-use conditions ('when the build is done and the website and brand are settled') plus an edge-case fallback ('or the customer stopped answering'), and a 'call once' constraint. It stops short of naming sibling alternatives (e.g. complete_onboarding) to disambiguate, so it is clear context but not full when/when-not routing.

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