memory_verify_tool

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

With no annotations, the description carries the full behavioral burden, and it does disclose the mutation effects (sets verified_at and verified_commit) plus several defaults (commit defaults to HEAD, confidence defaults to 1.0, project auto-detected from git root). It omits whether verification is idempotent, what happens if the item is already verified, permission/auth needs, and how it differs from revalidation — meaningful gaps for a state-mutating tool.

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?

The key fact — what state is written — is front-loaded in the first sentence, followed by a short rationale and a clean arg list. The prose is tight; the only mild bloat is that the args list repeats default values that also appear in the schema.

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 described, and the side effects and defaults are covered. Still, for an unannotated mutation tool with four undocumented parameters, the description stops short of the idempotency, failure-mode, and sibling-routing information an agent would need to invoke it confidently.

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 10 parameters, so the description must compensate, and it explains 6 of them with real semantics (method stored in history, commit defaults to HEAD, verified_by_id is a memory ID holding the verification artifact, project auto-detected). The remaining four (actor, session, request_id, operation_id) are undocumented in both the schema and the description, so compensation is only partial.

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+resource: recording that a memory item was verified, and names the exact state it writes (verified_at, verified_commit). That is far more concrete than the name alone. It does not, however, differentiate itself from the close sibling memory_revalidate_tool, leaving the agent to guess which one applies.

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?

"Verification, not provenance, is what earns confidence 1.0" implies why and when to use this tool, and the confidence default of 1.0 reinforces that intent. But there is no explicit when-not-to-use and no routing between this and memory_revalidate_tool or memory_update_tool, so the agent must infer the selection rule.

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