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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real value beyond them: the answer is scored out of 10 by fixed rules (STAR structure, personal contribution, concrete result, length, using the question's words), the person is never scored, and nothing is stored. The return shape ('what went well, one thing to fix and the next question') is also disclosed, which is helpful given there is no output schema.

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?

Purpose and usage triggers are front-loaded and almost every sentence carries information. The opening 'Job Spotter. Practise an interview, one question at a time.' repeats the title verbatim, which is minor waste, and the scoring-criteria sentence is dense but justified.

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 multi-turn, stateful tool with no output schema, the description does the essential work: it explains the two call modes, the scoring rubric, the output contents, and non-persistence. The remaining gap is disambiguation from jobspotter_interview_prep, which an agent selecting among Job Spotter tools would want.

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 goes beyond it by explaining the stateful relationship between parameters (role alone yields the first question; question+answer yields a score). The 'n' parameter and its next_n contract are only covered in the schema, not the description.

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+resource ('Practise an interview, one question at a time') and even explains the turn-taking mechanics: send role to get the first question, send question+answer to get a score. It never mentions the close sibling jobspotter_interview_prep, so the agent must guess how these two differ, which keeps it short of a 5.

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 concrete trigger utterances ('practise an interview with me', 'how was that answer?') that map cleanly onto the two modes, and the role/question+answer flow reads as an implicit when-to-use rule. There is no explicit when-not and no routing away from jobspotter_interview_prep, so it stops at clear-context-without-exclusions.

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