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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile needs no restating. The description does add genuinely useful behavioral context beyond them: records may be pending or anchored, and version 0.4 carries the content check as salted-commitment fields with no text — a notable data-availability caveat. It stops short of describing lookup-failure behavior (unknown hash, unanchored record) or output shape details.

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?

The core operation is front-loaded in the first clause, but the sentence is long and runs three distinct ideas together (record retrieval, how records come to exist, version-0.4 content-check semantics). 'A door writes one before it lets an agent's action run' is helpful framing but sits in the middle of the retrieval explanation rather than being separated.

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 one-parameter read tool with an output schema and full annotation coverage, this is close to complete: it explains what the record is, its lifecycle states, its content-check fields, and where the same data appears in a sibling tool. Missing only failure/not-found semantics and any note on the canonicalization rules the input hash must follow.

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?

With a single parameter at 100% schema coverage, the schema already defines sha256 as a 64-hex canonical digest. The description reinforces that the key must be the *canonical* SHA-256 and that it selects the record as the ledger stores it, but adds no encoding, casing, or normalization guidance.

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 gives a concrete verb and resource — 'Return one admission record (a2a-admission-v0) ... by its canonical SHA-256' — and says what the record contains (exact bytes, pending or anchored state, ledger entry once anchored). It differentiates from nenrin_resume by scope (single record vs. admissions[] listing) and implicitly from nenrin_ledger_entry by nesting the entry inside the record, though the latter relationship is left for the agent to infer.

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 clear by implication: fetch a single admission when you hold its canonical hash; use nenrin_resume when you want a relying party's anchored admissions as a list. The alternative is named explicitly, but there is no explicit statement of when *not* to use this tool or of what to do when the hash is unknown/unanchored.

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