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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description usefully adds that a repeat call returns the prior outcome rather than re-executing, which is real behavioral value. However it says nothing about what happens on a fingerprint mismatch, how ttl_s affects the stored key, whether the key is reserved or reused, or what an error looks like — all critical for an idempotency primitive.

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?

Two short sentences, front-loaded with the action and the conditional return, with no filler. It is on the edge of under-specification rather than bloat, but nothing written is wasted.

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 no output schema, the description must define the response, yet 'the prior outcome' is left undefined — an agent cannot tell whether it receives a status, a stored value, or a token. Combined with unexplained 'scope' semantics and an undocumented ttl_s default, the definition is too thin for a four-parameter stateful primitive.

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, so the description must compensate and largely doesn't: 'key', 'scope', and 'ttl_s' are not explained at all. The one note, 'fingerprint is a hex hash', merely restates the regex pattern already in the schema.

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 ('Start an idempotency key') plus the key semantic twist ('or return the prior outcome'), which tells an agent this call may be a no-op. It doesn't explicitly name idem.commit as the counterpart, so the sibling pairing must be inferred from the adjective 'begin'.

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?

Usage is only implied: 'begin' suggests a two-phase pattern with idem.commit, but the description never says when to call this versus committing, nor whether calling begin twice with the same key is expected. No exclusions or prerequisites are stated.

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