range_analysis

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

With no annotations, the description carries the burden of behavioral disclosure. It is honest that the tool cannot deliver full range analysis and 'reports that frontier honestly', which gives an agent accurate expectations about degraded/partial responses. But it does not disclose whether the operation is read-only, whether it can return empty results, or what kind of output structure to expect.

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 description is appropriately short and front-loaded; the first sentence identifies the primary behavior and the second clarifies the limitation. It loses a point because 'frontier' is used instead of a clearer term, and the two sentences are dense with unexplained jargon, making them less immediately useful than they could be.

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 four-parameter tool with no annotations, no output schema, and low schema description coverage, this description is not complete. The absence of parameter semantics, return shape, and usage against sibling tools leaves significant gaps for an agent trying to decide and correctly invoke this tool. The concise dismissal of full analysis is helpful but not enough.

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 only 25%, so the description must compensate, but it does not. There is no explanation of what 'value', 'function', or 'limit' represent in the context of range analysis, nor how 'format' interacts with the returned evidence. The vague phrase 'numeric evidence' is not sufficient to let an agent meaningfully choose or fill these 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 states a specific operation ('Return lightweight numeric evidence') and clearly scopes it to graph-guard-exposed situations. It also distinguishes itself from a fuller range-analysis tool by explicitly noting that full value-range analysis is unavailable. However, the phrases 'graph guards' and 'frontier' are domain-specific and not defined, which introduces some ambiguity.

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 gives a condition for use ('when graph guards expose it') and an exclusion ('full value-range analysis is explicitly unavailable'), which implies this tool should be used only for lightweight evidence rather than comprehensive analysis. It does not name alternatives or give explicit when-this-tool-versus-that guidance, but the limitation is clear enough to avoid overusing it.

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