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

Annotations already cover read-only, idempotent, non-destructive and closed-world. The description adds genuinely new behavioral context beyond them: it spends no agent credits, and reading requires a path taken from a prior search result. It doesn't cover result-set size or truncation, so not 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?

Four dense sentences: scope, exclusion, mode selection, cost. Front-loaded with purpose and immediately followed by the routing rule; no filler.

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?

Covers what is searched, how to invoke each mode, the mutual-exclusion rule, cost behavior, and the shape of each return (matching sections vs whole page). With no output schema needed and only two simple params, nothing an agent needs 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 coverage is 100%, so baseline is 3, but the description adds the crucial constraint that the schema does not encode: send exactly one of query/page. It also clarifies provenance of the page value (must come from a search result) and includes a concrete example format.

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 pair (search or read) and resource (Modem's public docs), enumerates the covered topic areas, and explicitly names what it is not for (organization data). An agent can separate it from the modem_agent_* siblings without opening any 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 both the positive routing ('answer how Modem works') and the negative routing ('Not for your organization's data; ask the Modem agent with modem_agent_invoke') plus the mode-selection rule: send a query to search, a page path from a result to read. Nothing is left to inference.

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