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

Beyond the readOnly/destructive annotations, the description discloses what is redacted (no emails, IP addresses, browser details), that MCP-tool-initiated changes are included, the newest-first ordering, keyset paging, and the `audit-log.view` permission requirement. That is substantive behavioral context an agent cannot get from the annotations.

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 with no filler; the core purpose leads, then paging mechanics, then the sibling disambiguation, then the permission gate. Every sentence carries load.

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 explained, and the description still covers ordering, paging, redaction, permission, and alternative routing. Nothing an agent needs to invoke this correctly is missing.

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 100%, so limit/since/cursor are already documented with defaults and bounds. The description's 'keyset-paged via cursor; since stops at a date' largely restates what the schema says about `since`, adding little new syntax or edge-case detail, so the baseline of 3 applies.

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 and resource ('Read the workspace audit log'), plus scope and ordering ('newest first'), and clarifies the payload ('who changed what, by name'). It is immediately distinguishable from siblings like get_proof_of_play and whoami.

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?

Explicitly routes the agent away from a plausible alternative: 'Use get_proof_of_play for what played on screens rather than who changed it.' That is a named alternative plus the condition that selects it, and the required permission is stated.

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