Smsc History

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

Annotations already declare readOnlyHint and openWorldHint, so the description only needs incremental context — and it delivers: pagination mechanics via prev_id, the important limitation that a complete walk does not prove archive retention, and that personal data and message text are withheld by default. Return-format details are covered by the output schema.

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 compact clauses, front-loaded with the core action and date format, then pagination, then caveats. No filler, though the retention caveat and the privacy note are terse enough to be slightly cryptic without domain context.

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 zero schema documentation, the definition covers the highest-risk semantics (date format, cursor loop, privacy defaults, retention caveat) but leaves the filtering and paging-size parameters unexplained. An agent could call it correctly for a basic walk but would be guessing about email/phone filtering and page_size/max_pages effects.

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 across 10 parameters, the description must compensate and only partly does: it specifies the DD.MM.YYYY date format for start/end, explains prev_id as the next_cursor carrier, and implies the include_personal_data/include_text defaults ('hidden by default'). It says nothing about email, phone, format, page_size, or max_pages, leaving half the surface undocumented.

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: 'Read one outgoing-history page'. The word 'outgoing-history' distinguishes it from smsc_read's single-message retrieval, though no sibling is named explicitly and the 'one page' scope is only clarified by the follow-up pagination sentence.

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 concrete operational guidance for pagination ('Follow next_cursor as prev_id until complete') and a scoping caveat ('this does not prove archive retention'), which implicitly frames it as a browsing/audit tool. However, it never says when to prefer this over smsc_read or smsc_analytics, so alternative selection 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.