Get problem

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds useful behavior: returns a parsed Pydantic model and raises MissingParameterError or ParameterError. However, that error claim sits in tension with a schema where problem_id defaults to null and no parameter is required, which is exactly the kind of ambiguity a behavioral note should resolve.

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?

The purpose sentence is front-loaded and short, but the body is raw Sphinx field markup with low-value lines such as ":rtype: Response" and ":type problem_id: str" that duplicate the schema and add no agent-relevant information.

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?

Hmm — no output schema exists, so the description is right to describe the return shape (a parsed Pydantic model), and it covers the primary identifier and failure modes. But with 15 parameters at 0% schema coverage, an agent has no idea what the remaining query/view/pagination parameters do or whether omitting problem_id is legal.

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 0% across 15 parameters, so the description carries the full burden, yet it only explains problem_id (typed as str here, while the schema allows integer or string). The fourteen sysparm_*, api_parameters, data, and name_value_pairs parameters get no explanation at all — including likely-useful knobs like sysparm_fields, sysparm_display_value, and sysparm_query.

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 first sentence gives a specific verb and resource ("Retrieve details of a specific problem record"), and "specific" signals single-record lookup versus the plural sibling servicenow_get_problems. It stops short of naming that sibling, so the differentiation is implied rather than explicit.

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?

Usage is implied by "specific problem record" plus the problem_id param — fetch one record when you have its sys_id. There is no explicit when-to-use/when-not or pointer to servicenow_get_problems for listing/searching, and no prerequisites or permissions noted.

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