Smsc Cost Report

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful interpretive context — currency/timezone are as-reported, incomplete pages must not be treated as period totals, and message costs differ from account charges — but says nothing about pagination limits (max_pages), auth, or rate limits.

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 short sentences with no filler, which is good, but the phrasing is compressed to the point of opacity — "one live history page" and "check complete and next_cursor" require the reader to infer the pagination model. Front-loading the scope constraint is fine; the density costs clarity.

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?

An output schema exists, so return values need not be explained, and the safety annotations are in place. However, a 5-parameter reporting tool with 0% schema coverage and no guidance on start/end format, pagination, or include_text is not complete enough for an agent to call correctly on the first try.

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 5 parameters at 0% schema description coverage, the description carries the full burden and largely fails: start/end formats and timezone handling are unspecified, and prev_id, max_pages, and include_text are never mentioned. The reference to "complete and next_cursor" describes output fields rather than input semantics, leaving the pagination mechanism (prev_id vs next_cursor) ambiguous.

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?

"Analyze one live history page" gives a verb and a scope, but "analyze" is vague about what the output is (cost totals? raw page contents?) and the description never explicitly says it produces a cost report over start/end. The clause "Message costs differ from all account charges" does narrow the domain somewhat, but it does not clearly separate this tool from siblings like smsc_history or smsc_analytics.

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?

There is no explicit when-to-use guidance and no sibling is named as an alternative, even though smsc_history and smsc_analytics are obvious candidates. The line "partial pages are not period totals" hints at a caution but reads as an output caveat rather than routing advice.

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