model_qc

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

Annotations already indicate this is not read-only, non-destructive, closed-world, and non-idempotent. The description adds useful behavioral context beyond annotations: it returns a durable report with severity/IJK CSV witnesses, includes independent volume/cluster accounting, and warns that connectivity is topological rather than flow connectivity. It does not contradict the annotations, since producing a durable report is consistent with readOnlyHint=false.

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 four dense sentences with no filler. It front-loads the core QC checks, then states return behavior and ends with two important scope caveats, each of which earns its place.

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 complex nested-parameter QC tool with no output schema, the description provides a clear summary of the checks and return artifacts. It is nearly complete, though it does not clarify whether execution is synchronous or job-based, despite execution, timeout, retry, and idempotency parameters in 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 100%, so all request fields, including nested execution options, project/properties references, region_field, and small_cluster_cells, are already documented in the schema. The description adds conceptual context through mentions of regional summaries and IJK clusters, but does not add explicit parameter-level meaning beyond the schema.

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 names a specific verb-resource pair, 'Numerical QC of an immutable model', and enumerates the exact checks it performs: trilinear geometry, property ranges, NTG/PORO consistency, zero pore volume, IJK clusters, and regional summaries. This level of specificity clearly separates it from generic validate/inspect siblings.

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?

Usage context is implied by 'Numerical QC of an immutable model' and the caveat that 'Geological fitness remains specialist review', but the description does not say when to choose this tool over alternatives such as result_validate, dataset_validate, model_diff, or regional_volumes. The exclusion is useful but incomplete as routing guidance.

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