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

No annotations are provided, so the description carries the full burden, and it meets it: it discloses that every call produces the refusal retrieval_mode_unavailable and that the refusal payload names the served modes and the data that would answer the request. The only gap is that it doesn't say whether the refusal is an error or an informational response, which affects how an agent should handle it.

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?

It is a single tangled sentence that leads with the negation 'Not served:' instead of the actionable fact, and phrases like 'which no build records' force re-reading. The most decision-relevant clause — every call returns a typed refusal — arrives late.

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 zero params, no annotations and no output schema, the description is the only source, and it covers what the tool yields and where to go instead. What it omits is how an agent should treat the refusal (fallback? retry? abort?) and which sibling to prefer between as_of and as_observed, leaving a decision gap.

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?

The schema declares zero parameters at 100% coverage, so there is nothing for the description to disambiguate; baseline 4 applies. The description does not waste words inventing phantom parameters.

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 does convey that this tool never returns data and always answers with a typed refusal naming as_of/as_observed, which lets an agent rule it out. But the opening 'Not served:' frames the tool by what it is not, and the resource it nominally covers ('what a reader could have known on a date') is buried mid-sentence, so the core fact — this is a refusal stub, not a capability — has to be inferred from the tail clause.

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?

It names the sibling modes (as_of, as_observed) and 'the data that would serve it', which is real routing signal. However, it never states the directive explicitly ('do not call this; use X for Y'), leaving the agent to infer that these alternatives are the correct path rather than an incidental listing.

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