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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses that hybrid mode 'ranks by meaning' while exact 'finds verbatim wording', which are not derivable from the schema. It also explains that each item is a snippet and that summaries are excerpts, and that get_activity provides the full body. These behavioral traits help an agent predict results.

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?

The description is four sentences, each carrying distinct information: scope, usage examples, mode semantics, and output snippet behavior. The main verb and resource are front-loaded in the first sentence, and the pointer to get_activity is placed at the end without redundancy.

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 9-parameter search tool with an output schema, the description covers the essential context: what is searched, optional filtering dimensions, mode behavior, and output item composition. It also handles the ambiguity of null parameters by stating 'optionally scoped', and it routes to get_activity for full bodies, closing the loop. The only minor omission is the limit parameter semantics, which is common enough not to be critical.

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?

With 0% schema description coverage, the description compensates by naming scoping dimensions: 'one record, actor, type, or date range', matching record_type/record_id, actor_id, types, and date_from/date_to. It also clarifies the mode enum values (hybrid/default, exact, semantic) and how query interpretation differs. It does not mention limit, but the core query parameters are explained.

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 opens with a specific verb and resource: 'Searches history' and enumerates the covered item types (notes, comments, calls, meetings, emails, messages, timeline updates). It also distinguishes itself from sibling search tools by scoping to activity history, not records or candidates. The 'what did we discuss' examples reinforce the intended domain.

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?

The description provides explicit use-case phrases: 'Use for "what did we discuss", "when did we last contact", "who said X"'. It also points to get_activity as the alternative for full bodies when summaries are insufficient. However, it does not explicitly state when not to use other search siblings, so it stops short of full exclusion coverage.

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