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

Annotations only declare it is a non-destructive write; the description goes well beyond by disclosing patch semantics, that fields in `locked_fields` are silently ignored because partner sync owns them, and that the response carries `is_published` and `missing`. That is exactly the kind of side-effect and return behavior an agent needs before calling a 25-param mutation.

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 core mutation behavior and ending with the read-first guidance. The closing clause 'this call returns the value as it now stands' is mildly redundant with the earlier `is_published`/`missing` statement but not wasteful.

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 25-parameter mutation with no output schema and only partial schema documentation, the description covers the essentials: partial-update semantics, sync-owned locked fields, and the key return signals. It stops short of documenting the full parameter surface or other response fields, but nothing critical for correct invocation 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 only 52% across 25 parameters, so the description must compensate. It adds the crucial patch-semantics rule (unsent fields are unchanged) that governs how every parameter is interpreted, but it does not clarify the undocumented params such as `length_unpin`, `check_in_periods`, or `min_charter_days` beyond what the schema already says.

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 ('Change details of one of the operator's boats') and immediately scopes it as a partial update ('only the fields sent change'). It also distinguishes itself from the read path by telling the agent to 'read the current value with its read tool first', routing it away from get_boat.

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 clear operational context: use it to mutate existing boats, only sent fields change, and read first to see the current value. It does not spell out explicit when-not conditions or name a competing update alternative, but for a straightforward update tool the usage is unambiguous.

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