evidence

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

No annotations exist, so the description carries the full burden and does: it discloses that totals are never computed (the caller must count/sum), recommends preferring items whose dates match the question window, explains cache replay at zero model cost for identical questions, and documents the RENOR_EVIDENCE_MODE gating plus the `force` escape hatch. That is unusually rich behavioral context for a tool with zero structured metadata.

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?

Five dense sentences, front-loaded with the core behavior before the usage guidance, the counting caveat, and the gating mechanics. Every sentence carries actionable information with no filler or restatement of the name.

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 annotations and no output schema, the description still covers what is returned (distinct items/events/amounts with dates), what is deliberately not returned (no computed totals), how caching affects repeated calls, and how the mode gate behaves. An agent has everything needed to call it correctly and interpret the result.

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 all three parameters are already documented with types and defaults. The description adds narrative meaning to `force` (run even when auto declines) but says nothing about `topK` or how it interacts with the second enumeration pass, so it only marginally exceeds the schema baseline.

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 ("Question-conditioned evidence extraction") and concretely describes the two-pass behavior: retrieval followed by enumeration of distinct items/events/amounts with dates. It also names the sibling it overlaps with ("Retrieves like search") and pins down the question class it is for, so an agent can distinguish it from `search` without opening a schema.

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?

"Best for how-many / how-much / count / list / aggregate questions about the user's history" gives an explicit when-to-use condition, and the gating note plus `force: true` tells the agent how to override a declined call. It stops short of explicitly saying which sibling to use instead for non-aggregate lookups, leaving that inference to the reader.

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