Conversations: Get Conversation Counts

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuine context beyond them: the REST endpoint and the required auth header ('api-access-token'), plus a note that Persian/Arabic-Indic digits and non-English text pass through unchanged. It does not say what the returned counts look like or whether they are paginated.

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 purpose in the first clause, then endpoint, auth and encoding notes on separate lines. No filler sentences, though the Persian-digit note is boilerplate that sits oddly on a counts endpoint that returns no text values.

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 read-only aggregation with fully described parameters and no output schema, the definition is serviceable but leaves an important gap: it never describes the shape of the counts returned (per-assignment buckets vs. a single total), which is the single most useful thing to know before calling it.

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 all six filter parameters are already documented in the schema and the baseline is 3. The description adds little beyond 'optional filters', and it introduces an 'assignment' dimension (mine/unassigned/assigned/all) that has no corresponding schema parameter — potentially confusing rather than clarifying.

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 ('Get conversation counts') plus the grouping dimension (mine/unassigned/assigned/all) and the backing endpoint, so the agent knows exactly what it produces. It does not name or contrast with overlapping siblings such as gapify_filter_conversations or gapify_account_conversation_metrics, leaving the agent to infer which one yields counts versus records.

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?

'with optional filters' implies the filtering use case, and the assignment groupings hint at dashboard-style aggregation. However, there is no explicit when-to-use/when-not guidance and no pointer to alternatives, which matters given several conversation-listing siblings that could be mistaken for this tool.

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