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

Annotations declare destructiveHint=true and readOnlyHint=false; the description goes beyond that by disclosing the cascading side effect ('eligible existing candidates are brought in line with the new criteria') and the exact undo contract. It stops short of saying what happens to candidates who no longer match after the change, which is the main residual risk for a destructive mutation.

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, each doing distinct work: scope of the update, side effect, and recovery path. Front-loaded with the operation and free of filler.

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?

Since there is no output schema, naming previousCriteria and previousDescription is a valuable addition, and the side effect is covered. But for a 19-parameter destructive mutation, the description leaves the nullable-clears-field question and most parameter semantics unexplained, so an agent still needs to guess at several behaviors.

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 19 parameters and only 5% schema description coverage, the description carries almost the full burden, yet it only clarifies the merge semantics (unsupplied fields are untouched). It says nothing about the many criteria fields (seniority_min/max, company_stage_match's 'any'/'all' behavior, nullable fields meaning clear-vs-omit), and the mention of previousCriteria targets result values rather than input parameters.

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 and adds the critical partial-update qualifier ('only the supplied criteria fields'), which distinguishes it from a full replacement or from create_role. It does not explicitly contrast itself with siblings like rerun_criteria_match or create_role, but the operation is unambiguous.

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?

The description names restore_role_criteria as the reversal path and explains the condition (pass previousCriteria/previousDescription unchanged), which is clear guidance for the undo case. It gives no guidance on when to prefer this tool over adjacent ones such as rerun_criteria_match, and states no prerequisites or exclusions for editing criteria.

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