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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description only has to add what they don't. "A failed lookup must not be treated as an empty list" is a genuine failure-mode warning not present in the annotations, but it is left cryptic — no indication of how a failure surfaces or what ordering/pagination to expect.

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 short sentences with no filler, and the workflow cue is front-loaded. Slightly telegraphic in places, but nothing is padding.

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?

It is a one-parameter read-only tool with an output schema, so the bar is low and the failure-mode caution covers the riskiest inference. Still, the description never explains what status selects, whether results are scoped to the current user, or how multiple results are ordered.

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% and the single required parameter status (enum: collecting/completed/abandoned) is never mentioned in the description. The only hint is "saved applications," which is ambiguous about whether abandoned or completed applications are included — the enum values do not resolve that on their own.

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?

"Recover your saved applications" names a resource and an action, but the verb is metaphorical where the tool is really a filtered list. Nothing distinguishes it from the sibling get_application, and the required status filter that defines the query is never mentioned.

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?

"Before starting or resuming work" implies the surrounding workflow (open_application_form, restart_application), which is useful context. But no alternative is named and no when-not condition is given, so the agent must infer that get_application is the single-record counterpart.

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