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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered; the description adds real semantics beyond that: de-duplication by line, first/last-seen timestamps, reappearance not counting as new, and the include_start exclusion. It omits pagination/result-size behavior despite limit/offset parameters, which keeps it from a 5.

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 what the tool yields, then differentiation, then exclusions, then filters - a logical order with no filler. The compressed phrasing ('Narrow it with 'text' (or a regex) and 'from'/'to'') is efficient but slightly telegraphic.

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 10-parameter read tool with no output schema, the description covers what is returned, the default exclusion rule, and most filters, which is enough to call it correctly. The remaining gap is pagination/limit behavior, which an agent may have to discover empirically.

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?

At 60% schema coverage, the description partially compensates: it clarifies regex mode for 'text', the from/to narrowing, still_there=false meaning 'removed', and include_start behavior. It says nothing about limit, offset, or case_sensitive, leaving three parameters to the schema alone.

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?

The description names the exact resource and shape of the result: 'every line that appeared on a monitor's page, once each, with when it was first and last seen,' and lists concrete examples (tour dates, line-up additions, headlines, changelog entries, products). It explicitly distinguishes itself from the sibling get_history, so an agent can pick between them 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?

'Better than get_history for lists that grow and shrink or pages that flip between layouts' gives both the alternative and the condition that selects this tool, plus the rationale (a returning line isn't new again). It also states the default exclusion of first-snapshot lines and how to change it, and points at filters for narrowing.

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