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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the description's added value is what it says about auth ('Requires OAuth'), scope ('does not search for people'), clause-preservation behavior, and the three-state feedback vocabulary (possible/partial/impossible). It never clarifies whether an edit is persisted (it is read-only, so presumably returned only) or what happens when status is 'impossible' — minor gaps kept it below a 5.

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?

Front-loads the core action, then tacks on constraints and prerequisites in short imperative sentences. No sentence is filler; even the exclusion and the resolve_company step prevent concrete failure modes.

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 only 3 fully-documented params and no output schema, the description carries the remaining burden and does: it spells out the return payload, the flow around the call (show user, then source), and the auth requirement. An agent has everything needed to call this correctly.

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 the schema already documents all three params and the baseline would be 3. The description goes beyond it by tying pdlQuery to the 'latest reviewed' query that must be passed unchanged and by specifying that a newly resolved company's name and LinkedIn URL belong in editRequest.

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 ('apply one clear recruiter change to the latest reviewed sourcing query') plus the output ('the edited query and feedback'). Explicitly bounds scope with 'This does not search for people', which separates it cleanly from source_candidates and build_sourcing_query.

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?

Gives real usage rules: one change at a time, keep unaffected clauses, show the edited query to the user before sourcing, and resolve any newly named employer with resolve_company first. It also names the exclusion (no people search) and the OAuth prerequisite, so the agent knows both when and how to call it.

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