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

With readOnlyHint=false and destructiveHint=false, the description goes beyond by revealing side effects ('this shapes where briefs, drafts, and lint formats anchor'), the confirmation requirement with the operator, and state-specific name handling. This adds meaningful behavioral context that annotations can't convey, only slightly short of 5 for not detailing error or reject 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?

A dense but efficient single paragraph. The contrast structure ('for X vs. for Y') earns its place, and the parenthetical showing naming conventions is high-value. Slightly long due to overlapping mentions of the UI, but each sentence adds operational information — strong but not minimalist.

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 simple parameters and no output schema, the description covers the essential complexity (the detected/planned state machine) completely. The mention of the operator-confirmation step and the 10-item limit round out the picture. Minor omission of the 'open' state and reliance on the UI for management keep it just shy of complete.

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 0% schema coverage, the description had to compensate — and it does, richly explaining type semantics (website vs. social handle naming conventions), and the two main state values. However, it omits the 'open' state enum value and doesn't address projectId at all, leaving minor gaps in an otherwise strong parameter walkthrough.

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 opens with a specific verb+object pair ('Add a destination to a project') and immediately scopes it with 'where the operator publishes.' The two-mode behavior (detected vs. planned) is clearly the tool's distinguishing feature. It doesn't explicitly contrast against a sibling like list_destinations, keeping it from a 5, but the core purpose is unmistakable.

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?

Excellent when-to-use guidance via the detected/planned distinction: 'for a destination that already exists' vs. 'one they intend to build.' It also conveys the 10-destination limit and directs the user to the web UI for management. Deduction for not naming a specific tool-based alternative, though the operational context is thorough.

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