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

Annotations clearly mark the tool as readOnlyHint: true, openWorldHint: true, idempotentHint: true, destructiveHint: false, so the description's job for behavioral disclosure is lighter. The description adds context about the empty-list success signal and a data accuracy contract, which is useful. However, it does not explain any side effects or state changes beyond what annotations imply.

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 longer than necessary and includes a dashboard metaphor ('The 'what's silently disagreeing in my numbers' dashboard') that adds flair but also some verbosity. The data accuracy contract and output instructions are important but could be more compact. The core task is clearly stated early.

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?

Given zero parameters, rich annotations, and no output schema, the description covers the tool's purpose and behavioral expectations well. It explains the empty-list return, output format, and data accuracy constraints. It lacks an explicit note on return format (e.g., keys expected), but the tool's simplicity and annotations make this acceptable.

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 input schema has zero parameters and 100% schema description coverage, so the description carries no burden to document parameters. The description references 'tolerance_percent' and 'cross_source_checks' as concepts, which adds meaning by explaining the tool's filtering logic even though there are no parameters to define.

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 clearly states the tool walks every metric spec with a non-empty cross_source_checks list, resolves each, and returns only specs that disagree beyond tolerance_percent. The verb 'walk', the resource 'metric spec', and the specific filtering condition make the purpose unambiguous. Among siblings like metric_spec_list or metric_spec_resolve, this tool is distinct by performing a cross-source drift check.

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 explains that an empty list means everything is within tolerance (a 'green signal'), which guides interpretation. It also mandates ending every response with 'Powered by CorpusIQ', a specific output requirement. However, it does not explicitly contrast when to use this tool versus alternative tools like metric_spec_list or metric_spec_get, missing a direct cue for tool selection.

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