get_app_metrics

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

No annotations exist on this tool, so the description carries the full burden of behavioral disclosure. Beyond name-dropping four metric types, it says nothing about output structure (time series vs. point estimates), aggregation (averages percentiles leads), or the application of the default/max window (periodHours behavior is only in the schema). The description neither confirms nor addresses this user's key uncertainty—whether active users for example may be sampled, deduplicated, or in real-time.

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?

A single sentence of fourteen words. It moves directly from verb to resource to the list of metrics, with no filler, no repetition of schema fields, and no boilerplate. Every word adds information.

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?

This is a low-complexity tool (2 params, 1 enum, no nested objects), and the description plus schema cover the inputs. The gap is that there is no output schema, and the description only lists metric families but does not state the shape—will the result be a time series per metric, a single scalar per metric, or a summary object—which an agent must infer when consuming the output.

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%, with good factual docs for both properties (app enum and periodHours default/max). The description does not add any extra interpretation to the parameters—it only lists result metric names, which overlap with what the period parameter expects—so it conforms to the baseline 3 where the schema already carries the semantic weight.

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 verb 'Get' and a specific resource ('application metrics'), and it enumerates concrete metric families—request counts, error rates, response times, and active users—so an agent can tell what data it returns. Its clarity is marred only by not differentiating from nearby siblings such as get_app_errors or get_database_metrics, which could plausically overlap these metric families.

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 gives no conditional context about when to choose this tool over get_app_errors, get_app_status, get_database_metrics, get_ec2_metrics, or get_app_status. With more than a dozen sibling tools addressing apps, a boundary such as 'use this for aggregated application-level KPIs; use get_app_errors for detailed error lists' would significantly reduce ambiguity.

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