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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses that existing applicants are re-evaluated immediately on creation and that refreshedCount reports how many suggestions changed — non-obvious side effects an agent must anticipate. It also makes the non-destructive scope explicit: suggestions never invite or reject anyone.

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 description is front-loaded with purpose and match semantics before drilling into condition grammar, which is good ordering. It is dense and slightly repetitive — the ALL-conditions match rule is stated twice — and embeds a schema-like structure in prose rather than relying on the input schema.

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 write tool with no output schema, it covers prerequisites, match semantics, per-field condition grammar, downstream effects, and even names the return field refreshedCount. An agent has everything needed to construct a valid call and anticipate its effects.

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%, but the description goes well past it by fully specifying the condition object grammar (type, operator, questionId, value) and constraints the schema only hints at: questionId required for type "question", "contains" unsupported for emailDomain, "exists" takes no value, and gt/lt are numeric and question-only. This is meaning the schema alone does not supply.

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 first sentence names a specific verb and resource ("Create an auto-review rule") and scopes it to this project's applicant screening, which cleanly separates it from updateApplicantRule and deleteApplicantRule in the sibling list. It immediately explains what the rule does downstream (suggested status + labels on match).

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 states the prerequisite (screening setup must exist, pointing to getScreeningSetup / configureScreening) and clarifies the rule only produces suggestions that a manager still reviews via reviewApplicants. It does not explicitly say when to use create versus updateApplicantRule, so a small routing gap remains.

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