Metric glossary

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real value beyond that: 'Static reference; no project data,' which tells the agent results are constant and not tenant-specific, plus an outline of the returned fields.

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?

Three tight sentences: the mapping purpose and routing trigger come first, the return shape second, and the static nature last. Nothing is padded or redundant.

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?

With no output schema, the description usefully enumerates what each entry contains, which is exactly what the agent needs. The only gap is the unexplained required organizationId, which is minor given the reference nature of the tool.

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 tool has one required parameter (organizationId) with 0% schema description coverage, and the description never mentions it. This is a notable omission for a tool described as a static, project-data-free reference — the agent gets no explanation of why an org id is required.

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 precise verb and resource — 'Map a plain-language or unfamiliar request to the right Mencoro metric and tool' — and immediately names the artifact it returns (each metric with synonyms, unit, range, direction, tool, example questions). This clearly separates it from data-fetching siblings like get_project or get_tracked_query.

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?

It gives an explicit, condition-based trigger: 'Call this first when a request is vague, non-technical, phrased in another language, or uses wording that does not match a tool name.' That is strong usage guidance, but it never juxtaposes this against near-neighbor reference/discovery tools such as get_mencoro_guide or get_available_filters, so the agent must infer which reference to pick.

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