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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses real output behavior: figures are counts only, no derived rates are produced, every figure is accompanied by its denominator/population, and thin stages are flagged as not readable as proportions. The trailing 'Read-only' merely restates the annotation, but that is redundancy rather than contradiction, and the suppression/denominator policy is genuinely useful context an agent cannot get from the annotations or output schema.

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?

Four sentences, front-loaded with what the tool produces and followed by the two behavioral guarantees (no rates, denominators always attached). The clause justifying why no rate is computed is slightly rhetorical but earns its place by explaining the deliberate omission; the only waste is the redundant 'Read-only' at the end.

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 shape need not be explained, and the description correctly focuses on counting and denominator policy. However, for a windowed analytics tool with three parameters (one required, one nested) at 33% schema coverage, the absence of any parameter guidance or sibling routing leaves the definition only minimally viable.

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 only 33% — the from/to date-time parameters are entirely undocumented and companyId's nested wrapper carries the generic note 'UUID value wrapper.' The description's 'over a window' obliquely signals that from/to bound the range but gives no format, optionality, default, or inclusive/exclusive semantics, and says nothing about the required companyId or its nested value object.

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 names the resource — the raise funnel and the commonalities among passes, over a window — but never states the operative verb ('returns'/'computes') directly and uses figurative language ('what the passes have in common') that requires interpretation. With roughly a hundred fundraising_* siblings (get_raise_plan, get_channel_ledger, get_insider_brief), it offers no differentiation from any of them.

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?

There is no statement of when to call this instead of fundraising_get_raise_plan, fundraising_get_channel_ledger, or fundraising_get_insider_brief, and no prerequisites or exclusions. 'Over a window' hints at a time-scoped analytics call, but the agent must infer the usage context entirely.

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