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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuinely new behavioral context: notes are untrusted prose (a prompt-injection caution) and the returned content is a privacy projection that is NOT a byte-for-byte export, with the content hash pointing to the full original. These are non-obvious traits an agent could not infer from structured fields.

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 sentences, zero filler, front-loaded with the read action before the trust and fidelity caveats. Every sentence adds distinct information (scope, trust level, projection caveat).

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?

An output schema exists so return structure need not be explained, and the description still previews the payload plus two important caveats (untrusted note prose, non-verbatim projection). The only real gap is entryId semantics, which is left entirely to the schema.

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% for the single parameter entryId, so the description carries the burden of explaining it but adds nothing about its format, provenance, or how it is obtained. 'One owned capture' gives only a vague hint that the id scopes to the caller's own entries; the pattern and length constraints live only 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 ('Read') and resource ('one owned capture') and enumerates exactly what the payload contains: user-written note, frozen evidence, assessment, briefing. The singular 'one owned capture' cleanly distinguishes it from the sibling list_notebook_entries without needing to name it.

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: fetching a single owned capture by id is the obvious counterpart to list_notebook_entries, and 'owned' hints that non-owned entries are out of scope. No explicit when-to-use, when-not-to-use, or named alternative is given, and nothing says what to do if the id is unknown or unauthorized.

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