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

Annotations already establish read-only, idempotent, non-destructive, non-open-world behavior, and the description adds genuinely new context: unlimited retention, comparison keyed by finding code and never by message, and URL-based matching for pre-watch runs. It stops short of covering ordering guarantees or pagination beyond the schema's limit.

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 sentences, front-loaded with the core purpose before the payload shape and the legacy-URL edge case. Dense but each sentence carries information; the retention remark is slightly expendable.

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?

With no output schema, the description usefully sketches the return shape (score, counts, change with delta and broke/fixed lists). Combined with annotations covering safety, an agent has enough to call it correctly; only parameter-level guidance and pagination behavior are thin.

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 67% (guest_token has no description), and the description adds nothing about `id`, `limit`, or the auth token — the newest-first/default-20/max-100 semantics live entirely in the schema. With partial coverage and no compensating text, this sits at the minimum-viable baseline.

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: reading a tab's previous runs and the deltas between consecutive runs. The described payload (score delta, appeared/disappeared findings) makes it unambiguous versus siblings like domain_history, weekly_site_report_history or list_tabs, which operate on other resources.

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?

"Every run has always been kept; this is where you read the series" implies when to reach for this tool, but no alternatives (domain_history, get_audit, list_tabs) or exclusions are named, and no prerequisites for the watch feature are spelled out. Usage is implied rather than stated.

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