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

Annotations only declare it is a non-readOnly, non-destructive, non-idempotent closed-world write. The description adds real behavioral context beyond that: the link is unclaimed for seven days, anyone holding it can open or claim it, and sign-in can retain it. It does not say what happens on repeat calls or how the returned link is formatted, so it stops short of 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?

Four sentences, front-loaded with the gating condition, then behavior, then prohibitions. Information-dense with no filler, though the closing prohibition list is packed tightly and reads as a run-on rather than structured guidance.

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 a valid output schema present, the description need not explain return values, and it covers the important sharing/claiming and expiry semantics an agent would otherwise miss. The remaining gap is per-parameter semantics for a nested schema with no field-level documentation, which is meaningful but not disqualifying for a save operation.

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 0% across four parameters with deep nested objects, so the description has to compensate. It adds meaning for provider_preferences (only explicitly supplied values) and roughly maps to job_ids and criteria, but title, sort_by, locked, and the location object are unexplained beyond schema structure, which is the minimum viable level.

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 description states the effect concretely: it persists reviewed criteria plus chosen public job IDs and 'Creates a seven-day unclaimed return link.' The verb (save) is implied through the title and the usage clause rather than front-loaded as an explicit purpose sentence, but an agent can tell what is produced and how it differs from curate_job_shortlist.

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?

Explicit trigger: 'Use only after the user explicitly asks to save reviewed criteria.' Explicit exclusions: 'Never call automatically' and no implication of application, employer contact, alerts, credentials, consent, or publication. It also bounds input scope ('Include only explicitly supplied provider preferences'), leaving little to inference.

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