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

Annotations already declare the read-only/non-destructive profile, and the description adds substantial context beyond them: the export is unsigned, it does not renew tokens or certify reliability, the JSON must be saved privately, and no credit is spent. These are the security, trust and cost facts an agent needs to reason about the result.

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?

Front-loaded with the core action and window, then auth/ownership scope, then return payload, then side-effect limits. Every sentence carries content, though the middle section is dense and list-like rather than cleanly segmented.

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, yet the description still usefully names the return shape (versioned JSON timeline, coverage/truncation notes, checksum, retained signed tokens). Combined with auth requirements, the 30-day window limit and the no-credit/no-sharing constraints, it is nearly complete for a 6-parameter tool; explicit start/end format for callers who miss the 'Unix-second' phrase is the main omission.

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 carries the burden and does so reasonably: the Unix-second window maps to start/end, 'up to five owned watches' maps to watch_ids, and the 'agent's separate owner key even for public agents' maps to agent_api_key/agent_id. The distinction between api_key and agent_api_key is implied rather than spelled out, leaving a small gap.

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 (export) and resource (private retained incident evidence) plus scope (UTC Unix-second window within 30 days). It also distinguishes itself from signed-evidence siblings by noting the export is unsigned, so an agent can separate it from agent_signed_evidence without opening a 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 clear boundaries: free read of own diagnostics, up to five owned watches, optional agent history requiring the agent's separate owner key, and explicit non-actions (no public sharing, new checks, registration or credit spend). It does not name the alternative tool an agent should call when it needs signed or certified evidence, so routing guidance is present but not fully explicit.

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