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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and non-destructive, so safety is covered. The description's only added behavior is 'Changes nothing' (a restatement of readOnlyHint) and the scope of what is read. It does not disclose ordering, recency window for 'recent verdicts', volume/pagination, or what happens for a client with no expectations, which are the real open questions for a read tool.

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 sentences, front-loaded with the resource and immediately followed by the three data categories; the closing 'Changes nothing' is a useful safety tagline rather than filler. Minor loss: the parenthetical 'every change and the result it should bring' defines the domain in the middle of the sentence and slows the front-loading.

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?

There is no output schema, so the description must convey return shape; it does so at a high level (three categories, 'with their numbers') but never explains structure, verdict values, or date semantics. For a single-param read tool with annotations, it is adequate but under-specified on returns.

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?

One parameter at 100% schema coverage ('Client name from list_clients'), so the baseline is 3. The description adds no meaning beyond the schema — no guidance on name normalization, ambiguity, or what the client string selects among.

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 concrete verb set (reads the ledger) and the exact data returned: open lines, lines needing manual verdict, recent verdicts with numbers. Distinguishes from siblings expectation_add and expectation_verdict by being the read path. Slightly opaque domain jargon ('expectations ledger', 'pass/fail rule checked on a date') leaves an agent guessing what an 'expectation' record actually is, but the read-only enumeration of returned data is specific.

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?

The description implies usage (inspecting verdicts before/after writing them) and its 'Changes nothing' clause plus the sibling names expectation_add/expectation_verdict imply the write alternatives, but it never says explicitly 'use this before expectation_verdict' or 'use expectation_add to create'. The division of labour with siblings is left implicit.

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