evidence_store

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

Annotations only declare the basic profile (write, non-idempotent, non-destructive, closed-world). The description adds genuine behavioral content beyond that: automatic secret redaction, immutability of stored evidence, content-addressing, and a human-review requirement for free text. It still omits failure modes and permission requirements, and the non-idempotent annotation sits somewhat awkwardly against 'content-addressed'.

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 dense sentence that front-loads the primary action (redact and store) before the caveat. No filler, though the semicolon clause compresses a precondition into a phrase that could be clearer.

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 six required parameters, two enums, a nested artifact object, and no output schema, this is a complex write tool that needs more than one sentence. Missing are parameter semantics, what counts as 'structured secrets', how redaction failures are handled, and what the caller receives on success.

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 0% across six required parameters, including a nested free-form artifact object, so the description carries the full burden. It gestures at 'structured secrets' (artifact) and 'free text' (description) but never maps meaning to project, kind, source, or captured_at, nor explains the enum vocabularies or the artifact shape.

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 two specific actions on a concrete resource: redacting structured secrets and storing immutable, content-addressed evidence. It is clearly distinguishable from siblings like evidence_read (retrieval) and memory_store (memory), though it never names those alternatives explicitly.

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 supplies one real precondition — manually review free text before import — which tells the agent how to prepare input. However, it gives no guidance on when to choose this tool over evidence_read, memory_store, or finding_correct, so the usage boundary is only implied.

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