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

Annotations already flag readOnly/idempotent/non-destructive, and the description adds substantially: the comparison basis is 60 roles' typical asks phrased by region (Kenya, Gulf, India, UK, US), the results are 'typical asks, not a real posting', and outputs are a count 'never a percent'. That caveat plus the follow-up instruction is exactly the context 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?

Correctly front-loads the trigger before the mechanics, and every clause is substantive. The second sentence is nonetheless very long, stacking role families, regions, five return fields and a caveat in one breath – readable but denser than ideal.

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?

With no output schema, the description carries the return-value burden and does it: up to 3 roles, the asks-count, strongest matches, first gaps, own-title match, and search links. It also sets the boundary that this is a starting point, not a tailoring target, which is everything an agent needs to call and interpret it correctly.

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 resume_text and location are already documented. The description only indirectly adds meaning by saying it returns 'search links for openings near them', implying location drives those links, but gives no format or default detail beyond the schema. Baseline 3 is appropriate.

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 ('suggest roles' from a resume) and scopes it to reading the resume against 60 named role families. The opening 'Use this when the user asks what jobs or roles they could apply for' makes it clearly distinct from match_job and tailor_resume, which need a real posting.

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 an explicit trigger ('user asks what jobs or roles they could apply for'), names the alternatives to use next ('ask the user for a real opening and run match_job or tailor_resume on it'), and states an explicit prohibition ('Never tailor a resume to the typical asks'). Nothing about when to use or avoid is left to inference.

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