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

Annotations declare readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false — a non-idempotent, non-destructive call. The description adds that it produces a narrative explanation ('so Medusa can explain what happened and when'), but doesn't mention the non-idempotency, side effects, or auth context. It doesn't contradict annotations but adds limited behavioral depth.

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 well-formed sentence with the verb and resource front-loaded, plus the endpoint hint. No filler.

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 single-param audited read with no output schema, the description is thin — it doesn't explain the response shape, the time window for 'recent', or how to pass credentials. Adequate but leaves gaps an agent must fill by guessing or reading external docs.

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 100% (single 'body' param with a description pointing to the OpenAPI schema). Description adds nothing about the body content and the schema itself is thin ('See the AffixIO OpenAPI schema resource'), so baseline 3 is fair but no extra value is added.

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 ('read') and resource ('recent trust events for an agent credential') and even names the endpoint. It's clear what it does, though it doesn't sharply differentiate from sibling affix_merkle_audit or the other affix_agent_trust_* tools.

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 description says what it does but not when to choose it over siblings like affix_agent_trust_verify or affix_merkle_audit. No exclusions, prerequisites, or alternative-routing guidance.

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