analyze_growth_query

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

With no annotations, the description carries the full behavioral burden. It does disclose something valuable and non-obvious: the response includes the exact filtered record count and calculation metadata for auditing, implying a deterministic, inspectable read operation. It does not state that records are left unmodified, whether the tool requires auth, or any cost/latency characteristics.

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?

Front-loaded with the core purpose in the first sentence, followed by scannable lists of filters and metrics. The enumeration of metrics is long but earns its place by telling the agent what questions are answerable. Minor redundancy between the filter list and the general capability statement.

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?

An output schema exists so return values need not be re-explained, and the description adds useful scope on filters, metrics, and audit metadata. However, with 0% schema coverage on three parameters, an unclear `source` input, and no sibling routing guidance, an agent is left guessing on several call-critical details.

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 coverage is 0% for three parameters, so the description is the only source of parameter meaning. 'Natural-language ... question' loosely maps to `query` and 'over supplied records' loosely maps to `records`, but the `source` parameter (default 'client-supplied') is entirely unexplained, as is the expected shape of `records` objects. The description only partially compensates for the coverage gap.

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?

States a specific verb and resource: 'Answer a natural-language growth analytics question over supplied records.' An agent can distinguish this from siblings like calculate_growth_metrics or compare_campaign_metrics because the input is free-text plus analyst-supplied records. It does not, however, name the sibling it competes with, so routing still requires inference.

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 scopes the tool usefully by listing supported filters (campaign names, platforms, ISO date ranges) and supported metrics (ROAS, revenue, CTR, etc.), which lets an agent judge whether a given question fits. But it gives no explicit when-to-use vs. when-not guidance and never points at the alternative sibling tools for non-natural-language or non-supplied-record cases.

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