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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds real value beyond them: it discloses that every change creates a new revision, is reversible, and that a human-readable result lands in the `say` field. Permission requirements remain unstated.

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?

Three tight sentences with the purpose front-loaded and no filler. The trailing `say` note is slightly cryptic but is short and operationally useful.

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 mutation tool with no output schema and thin schema documentation, the description supplies the key missing context: mutability semantics, reversibility, accepted inputs, and the summary field. Absent permissions or interaction notes keep it short of a 5.

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 only 20%, so the description must compensate, and it does: it explains cv/cover_letter as text payloads, gives cv_variant's own/tailored values, and defines answers as {question: answer}. It leaves the relationship between cv and cv_variant partly implicit, but covers four of five parameters meaningfully.

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 (change/edit) and resource (an application's materials), and enumerates the mutable fields. It is distinguishable from sibling writers like prepare_application or apply, though it does not name any sibling explicitly to sharpen the contrast.

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?

It tells the agent what payloads are acceptable (cover_letter, cv, cv_variant, answers) but never states when to reach for this tool versus prepare_application, upload_cv, or apply, nor does it surface the undo_change sibling that its 'can be undone' claim depends on. Usage is implied rather than routed.

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