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

The description adds meaningful behavior beyond annotations: it discloses that results are computed on every row, returned in this response, and that the tool abstains rather than guessing when the question is not a read. It does not cover permissions, failure modes, or output shape, but the abstention and scope disclosure are valuable.

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 three tight sentences with zero waste, front-loading what the tool computes before the abstention behavior and the timing reference.

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 read-only aggregate tool with no output schema, the description covers what is computed, the abstention path, and when it applies. It could more explicitly explain the prerequisite relationship with path_resolver and what the returned answer contains, but nothing critical is missing.

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 objective, dataset_ref, and resolution_id. The description adds only indirect context via the path_resolver timing note; the baseline of 3 applies when the schema carries the parameter documentation.

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 (a read of the data) with concrete examples (total, average, count, top group) and scope (computed on every row, in this response). It does not clearly differentiate from siblings such as path_resolver, path_bespoke, or path_estimate beyond a passing timing reference.

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 is implied through the abstention note: when the question is not a read, the tool says so and names the next step. However, it does not explicitly state when to use this tool versus path_resolver or path_estimate, leaving the caller to infer the workflow.

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