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

With only destructiveHint=false declared, the description carries real weight: it discloses that holdings are NOT restored (only handle and words), that the api_key acts as ownership proof, and that a prior export is required. This adds behavioral context beyond the annotation, though it omits what happens on a bad key or a repeat call.

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?

A single dense sentence, front-loaded with the routing cue 'instead of join' before the precondition and effect. Every clause carries information, though the clipped, lore-heavy style costs a little immediate legibility.

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 2-parameter tool with full schema coverage and no output schema, the description supplies the essential recovery semantics, prerequisites, and data-scope limits. Only failure-mode and idempotency details are missing, which are minor here.

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 100% and the schema itself is unusually rich for api_key, so baseline is 3. The description still adds value by naming the provenance endpoint (GET /v1/me/export) for the record and tying the key to the export, which the schema does not state.

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 verb+resource is clear (reclaim/restore a lost identity, yielding your handle and words) and it explicitly contrasts itself with the sibling 'join'. However, the metaphorical phrasing ('this world lost you') requires the agent to infer that the resource is account/identity recovery, and the scope statement 'not what you held' is oblique.

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?

It gives an explicit precondition ('only if this world lost you') and names the alternative ('instead of join'), so the agent can route between join and reclaim. It lacks explicit failure/edge guidance, but the core when/when-not/alternative routing is present.

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