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

The 'Effects' line explicitly enumerates the three state changes (application created, posting -> applied, touch logged), which is exactly the mutation detail annotations cannot convey beyond destructiveHint=false. It also discloses the duplicate-guard behavior and the 'unknown' date escape hatch, so the agent knows the failure mode and the sanctioned edge case.

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-loaded with the core action, then the constraint, then the edge cases, then effects — a sensible ordering. Minor redundancy between 'One per posting.' and 'One application per posting (JH-4)', which restate the same rule.

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 non-idempotent mutation with no output schema, the description covers side effects, the duplicate constraint, and the unknown-date case, which is most of what an agent needs. Missing pieces are what a successful call returns (application id?) and what the channel parameter means.

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 80%, so the baseline is 3. The description reinforces applied_at's 'never guess' rule and resume_version's intent, but it says nothing about 'channel', the one parameter whose schema description is empty — even though its enum values (easy_apply, portal, email, agency_submission) determine the audit trail.

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 — 'Record an application actually submitted' — which distinguishes it from hunt_add_posting (creates the posting) and hunt_evaluate_posting (pre-submission). It does not name hunt_correct_application or hunt_set_application_status, so the boundary with those siblings is left implicit.

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 a concrete usage rule ('One per posting') and explains the duplicate guard's purpose so the agent understands when a duplicate rejection is intended rather than an error. It also tells the agent what to do when the date is unknown. It stops short of routing to alternatives such as hunt_check_duplicates beforehand or hunt_correct_application afterwards.

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