audit_log

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and closed-world, so the safety profile is covered. The description usefully adds that this is specifically the *write* audit trail (create/update/delete events) and gives the default limit of 50, but says nothing about retention, ordering, or how far back the trail goes.

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?

Three short, front-loaded sentences with no filler; the core purpose comes first and the filter/default details follow. Slightly terse for a six-parameter tool but structurally sound.

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?

For a 6-parameter, no-output-schema tool, the description covers the main query concept but leaves two parameters (including the required vault and the opaque is_memory_sink_write flag) and the timestamp semantics undocumented. Adequate to attempt a call, but the agent will likely need to guess on those fields.

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?

With 0% schema description coverage, the description carries the full burden, and it only partially does so: it maps note_path, op, and time (since), and states the limit default. The required 'vault' parameter and 'is_memory_sink_write' are never mentioned, and 'since' is left ambiguous (epoch seconds vs ms) despite the numeric format.

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 ('Query') and resource ('write audit trail for a vault'), and the filter dimensions (note path, operation type, time) make the scope concrete. It does not, however, distinguish itself from lookalike siblings such as index_runs or recent_notes, so the agent must infer which log this reads.

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?

No when-to-use guidance, no alternatives named, and no exclusions. The mention of what it can be filtered by is a capability statement, not routing guidance, so the agent gets no signal on why it would pick this over recent_notes or index_runs.

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