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

Annotations already declare readOnly/openWorld/non-destructive, and the description goes well beyond them: it explains per-name resolution outcomes (unmatched, ambiguous, duplicated), that such a name yields no column rather than a zero cost, that prices are rounded server-side and dated by `provenance`, and that outcomes surface in a `resolution` field. That is real behavioral context an agent could not infer from annotations.

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?

Front-loaded with purpose and the key routing rule in the first two sentences, then resolution semantics and pricing caveats. Every sentence carries information, though the resolution/reporting sentence is dense and slightly run-on relative to the rest.

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 values need not be enumerated; instead the description covers the parts an agent must know — model resolution semantics, the no-column-on-failure rule, preset-restricted volume, and pricing provenance. Nothing material is missing for correct invocation.

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 100%, so the schema already documents both parameters (the 2-4 name array with example and the volumePreset enum with default) — baseline 3. The description adds genuine meaning on top: names are resolved against the catalogue with explicit failure modes, and the volume-preset constraint is tied to a routing decision (outside 10k/100k/1m, use another tool).

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 (compare), resource (2-4 named LLM models), and the scope it operates over (all 8 use-case profiles at a chosen monthly volume, returning list and optimized cost). This is clearly distinguishable from siblings like recommend-llm-model and estimate-llm-cost without opening a schema.

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?

Explicitly says when to use it (user names specific models to weigh against each other, rather than filtering the whole catalogue) and when not to, naming the alternative: 'If they also supply their own token counts, or a volume outside 10k/100k/1m, use estimate-llm-cost instead.' Both the positive and negative selection conditions are spelled out.

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