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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds material context the annotations cannot: share publishes a public expiring link, it needs manage permission, and results are valid only when both audits share strategy and device, with source-changed metrics flagged inconclusive. This is rich disclosure beyond structured data and is consistent with readOnlyHint=false.

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 tight clauses, no waste: action first, then the share guard, then the result-validity caveat. Front-loaded with the core purpose and each sentence carries distinct information.

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?

Output schema exists so return format need not be explained, yet the description still adds the crucial output conditionality (shared strategy/device, inconclusive deltas) that an agent needs to interpret results. Combined with the share-safety guidance, nothing material is missing for a 4-param tool.

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%, so baseline is 3. The description raises it by adding governance semantics the schema lacks: share requires explicit approval and manage permission, and defaults to off. The A/B orientation is already in the schema, so no further credit is earned there.

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?

Specific verb+resource ('Compare two audits') with a unique role no sibling tool fills (get_audit_report, share_report, get_audit_history all do different things). It adds the default non-publishing posture and the delta computation condition, so an agent knows exactly what it does without opening the schema.

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?

Gives explicit conditions for the risky path: set share:true 'only with explicit approval and a connection that has manage permission.' This is clear when/when-not guidance for the write behavior. It stops short of routing the agent away from or toward sibling audit tools, so 4 rather than 5.

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