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

Annotations already cover readOnly/idempotent/non-destructive, and the description goes beyond them by disclosing determinism ('One number, the same every time') and partial-read behavior ('Partial = not fully read'), which an agent needs to interpret results correctly. It stops short of saying what a partial result looks like or how matching is weighted.

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?

It is short and front-loaded with the score and its range, but it is written as a telegraphic fragment chain rather than clear prose, and phrases like 'CVEmber' and 'how much its lines show' cost more comprehension than they save in length.

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?

There is no output schema, and the description does supply the essential return shape ('One number' on a 0-100 scale) plus the determinism and partial-state caveats. What remains missing is how the sub-scores roll into the single number and what a partial result physically looks like.

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?

With 67% schema coverage, the baseline is near 3. The description does add meaning for the optional job description ('how well it matches the job when one is given'), but the jobDescription parameter itself is undocumented in both schema and description, and no guidance is given on how keywords interact with resumeId.

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 description identifies the resource (a resume) and the output (a 0-100 CVEmber score) and breaks the score into completeness/readability, job-match, and line-quality components. It never names a sibling such as get_resume or tailor_resume, so the differentiation from those is left implicit, and the phrase 'how much its lines show' is opaque jargon.

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?

There is no explicit statement of when to call this versus get_resume (raw content) or tailor_resume (rewriting). The only usage-adjacent signal, 'Partial = not fully read,' describes a result state rather than guiding tool selection or naming an alternative.

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