pws_update_segment

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

The annotations only declare destructiveHint=true and readOnlyHint=false, but the description adds substantial operational context beyond that: it preserves unrelatted fields (partial update), validates the live show, writes transactionally, verifies the saved segment after writing, and gates mutation behind a preview=false+confirmed=true requirement. These are meaningful behavioral facts an agent needs to call the tool safely, and none contradict the annotations.

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 single dense, front-loaded sentence that states the core purpose first, then packs five behavioral guarantees into compact clauses. Every clause earns its place: preservation, validation, transactionality, verification, and the confirmation gate. No fluff or repetition of schema content.

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 destructive, nested-schema tool with no output schema, the description covers the essential operational aspects: what it mutates, how partial updates behave, the validation/write/verification pipeline, and the safety gate. It does not describe return values or error behavior (e.g., what happens when validation fails), which would have been valuable given there is no output schema. Still, the core calling contract is well covered.

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 50% — preview and confirmed have descriptions, but segmentId and changes do not. The description compensates by clarifying the critical parameter relationship ('requires preview=false plus confirmed=true to mutate') and the partial-update semantics of the changes object ('Preserves unelated fields'). The many sub-fields inside changes rely on the schema's type/constraint info, which is adequate.

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 states a specific verb pair ('PREVIEW OR UPDATE') and a specific resource ('ONE EXISTING MATCH/ANGLE'), making the tool's scope immediately clear. It distinguishes itself from siblings like pws_remove_segment (deletion) and the many pws_get_* read tools. The 'ONE EXISTING' qualifier also disambiguates it from creation tools like pws_create_event or pws_apply_show_plan.

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?

The description provides clear workflow context: preview first, then mutate only with preview=false plus confirmed=true. It also implies partial-update usage via 'Preserves unelated fields' — send only the fields you want changed. However, it does not explicitly name alternative tools or state when not to use this tool versus siblings like pws_remove_segment or pws_get_state.

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