read_file

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

With no annotations, the description carries the full burden, and it delivers meaningful behavioral disclosure: cost/latency ('MODERATE — one round trip to storage', where the dash explains the label), exact return shape (etag first line), and the critical optimistic-concurrency contract with write_file. It omits error behavior (missing file, permissions), but the decision-relevant traits for an agent are covered.

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 terse sentences with zero filler; the etag hand-off, round-trip cost, and concurrency behavior are packed efficiently. The 'MODERATE' tier is self-explained by the following dash clause, and the key imperative 'Search first' is placed last rather than front-loaded — a minor structural flaw.

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 single-parameter tool with an output schema and no annotations, the description covers the essentials: purpose, return format, concurrency contract, and a workflow hint. Minor gaps — path format specifics and behavior on missing files — are acceptable at this simplicity level. The description is complete enough for an agent to call the tool correctly without opening 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%, so the description must compensate, but it barely does. 'the note' and 'storage' loosely tie the `path` parameter to a note in storage, yet no format, resolution rules, or allowed values are given. The parameter's meaning is left almost entirely to inference from the tool name and parameter name.

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 uses a specific verb ('Returns') with a concrete resource ('the note') and discloses the distinctive return format (`etag:` first line). The 'Search first' line hints at its place in the sibling workflow, giving partial differentiation. However, the primary read operation is stated indirectly, and it does not distinguish read_file from list_files or context, which could also return note data.

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?

'Search first' is an explicit workflow directive — search should precede reading — which gives the agent real usage context. But there is no statement of when to prefer read_file over list_files or context, and no exclusions or conditions are given. Selection criteria are implied rather than stated, so guidance is thin but present.

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