swsd_create_problem

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

Goes beyond the annotations by disclosing retry semantics: 'WRITE — does not retry on transient failure; the agent should verify with swsd_get_problem before retrying.' This matches and enriches the idempotentHint=false/readOnlyHint=false structured hints. It doesn't cover auth/permission requirements or any side effects beyond creation, but the retry and verification guidance is concrete operational value.

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?

Front-loaded with the action, then required vs. recommended fields, then return value, then usage context, then the write/retry caveat. Every sentence contributes distinct information with 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?

Despite having no output schema, it states 'The created problem's id is returned for follow-up calls,' covering the return value. All 7 parameters are schema-documented, the write/retry behavior is disclosed, and the verification path is named, so nothing needed to call it correctly 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 100%, so the baseline is 3, and the description earns above that by adding a recommendation ranking the schema does not carry: 'Required: name. Strongly recommended: description, priority, category.' That tells the agent which optional fields materially affect record quality, which is information not present in the schema's required list.

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 ('Create a new SWSD problem (ITIL problem record)') and distinguishes the artifact from the sibling incident/service-request creation tools by qualifying it as an ITIL problem record. The parenthetical clarifies the domain concept so the agent doesn't confuse it with swsd_create_incident.

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?

Explicitly gives the trigger condition: 'Use this when promoting a recurring incident to a problem record so root-cause analysis and known-error tracking can be tied to multiple incidents.' It also names the follow-up path (verify with swsd_get_problem before retrying). It stops short of naming an explicit alternative (e.g. use swsd_create_incident for a one-off occurrence), so it's clear context without full when-not routing.

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