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

With no annotations, the description still discloses two meaningful traits: the output is an Ed25519-signed receipt and the call costs one metered event. However, it says nothing about whether state is mutated, permission requirements, or failure modes for a tool with nested object input.

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 compact sentence with the diff action front-loaded and the return value appended. Efficient, though the jargon density slightly reduces immediate legibility.

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 complex tool with 4 params, a nested object, zero schema descriptions, and no output schema, the description is thin. It usefully names the signed-receipt return (compensating for the missing output schema) but leaves parameter roles and call sequencing unexplained.

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 coverage is 0%, so the description must compensate, yet it only vaguely implies post_text and a snapshot. It never disambiguates the critical snapshot vs snapshot_ref pair, nor explains event_id or why snapshot is a nested object. Only post_text's role is inferable.

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 operation: diff post-compaction context against the pinned snapshot and return an Ed25519-signed receipt. This distinguishes it from siblings like snapshot/pin, though the terms 'post-compaction context' and 'metered event' are dense jargon that assume domain familiarity.

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?

The word 'post-compaction' implies a timing condition but the description never explicitly says when to call audit versus pin, snapshot, or reinject, nor does it state prerequisites or exclusions. The agent is left to infer the workflow.

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