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

Annotations only declare a safe read (readOnlyHint=true, destructiveHint=false). The description adds substantial behavioral context the annotations cannot: the AI-backed drafting (with named models), the guard that strips figures/names/tools absent from the user text, the [X%] placeholder convention, and graceful degradation to the rule-based result with ai.message explaining the failure. This is exactly the kind of beyond-annotation disclosure that earns a high score.

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 core function is front-loaded, then output shape, then AI/fallback behavior — a sensible order. It is dense but mostly earns its place; the specific model version names (Gemma 4, Llama 3.3 70B) are arguably more detail than an agent needs for selection.

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-shape burden well, naming score, verdict, fixes, up to three rewrites, and the ai.message fallback field. It is complete on behavior and output; only explicit when-to-use guidance is missing.

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 100%, so role, bullet, and company are already fully documented. The description's 'keep every fact as given' and placeholder notes speak to output content rather than parameter syntax, adding little beyond the schema. Baseline 3 applies.

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: check one resume bullet against fixed rules (score, verdict, fixes) and produce up to three rewrites. The singular 'one resume bullet' plus the rewrite emphasis distinguishes it from the plural check_bullets sibling. An agent can tell what it does without opening the schema.

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 the phrasing (improve a single bullet, get rewrites) but there is no explicit when-to-use routing or exclusion against alternatives like check_bullets or tailor_resume. The agent must infer that this is the single-bullet improvement path.

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