save_variant

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

Annotations only declare the write/safety profile (readOnlyHint=false, destructiveHint=false), but the description adds the critical non-obvious trait that this is a whole-object replacement, not a merge ('It replaces the variant whole, so pass every field it should define'). It also discloses pre-save reference validation ('Every reference is checked before saving') and the return payload ('Returns `saved` and the `variant`'), which annotations cannot convey.

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?

Purpose is front-loaded in the first clause, followed by usage, replacement semantics, conditional requirements, validation, and return value in five tight sentences. Every sentence carries information an agent needs; no filler.

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 an 11-parameter mutation tool with no output schema, the description covers the risky parts: overwrite semantics, the inheritance/id-discovery workflow, conditional required fields, and the return keys. Combined with 100% schema coverage, an agent has enough to call it correctly without guessing.

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%, so the baseline is 3, but the description adds real semantics beyond it: conditional requirement logic ('A variant without `extends` needs `title` and `summary`') that the schema itself does not encode (only `id` is required there), plus the inheritance rule 'set only what differs'. It does not add format or ordering detail beyond the schema's own descriptions.

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+resource ('Create or replace a CV variant') and immediately defines the domain object as 'the plan for one kind of role (title, summary, which bullets and skills to show)'. An agent can distinguish it from list_variants and the set_*/upsert_* siblings without reading any 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 ('set up a variant or tailor one to a job post') and names the read alternative with an ordering instruction ('read the current ones with list_variants first'). It also points to where ids come from ('list_variants → `own` shows them'), leaving little to inference.

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