swsd_update_problem

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, so the safety profile is covered. The description adds genuinely new runtime context beyond that: "WRITE — does not retry on transient failure," which tells the agent a failed call must be re-issued deliberately rather than assumed to self-heal, and it explains that text fields are full replacements rather than merges.

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?

Four short sentences, front-loaded with the action and the minimal call shape, then moving to the partial-update contract and the retry caveat. The sentence about replacing the description is nearly duplicative of the schema's per-field notes, which is the only wasted line.

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 12-parameter mutation tool with no output schema, the description covers the essentials an agent needs: partial-update behavior, full-body replacement for text fields, and non-retrying write semantics. Remaining gaps such as permission requirements and what the response contains are minor given full schema coverage.

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 every one of the 12 parameters already carries its own documentation, including the id digit-count auto-detection. The description only reinforces the replacement semantics that the schema already states per-field ("replaces existing"), adding little beyond the baseline.

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 ("Update an existing SWSD problem") and immediately clarifies the input contract ("Pass `id` and any fields to change"). It reads distinctly from swsd_create_problem and swsd_get_problem, though it never names a sibling to route against.

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?

Useful patch semantics are spelled out ("Only provided fields are sent — others stay as-is"), which tells the agent how to apply a partial change. However, there is no guidance on when to prefer this over a state-specific sibling like swsd_update_task_state, nor any stated preconditions such as looking up valid states or categories first.

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