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

No annotations exist, so the description carries the behavioral burden. It does usefully disclose that the result is an exact total for the whole account (no filtering), but says nothing about permissions, whether archived/deleted records are included, or performance/cost of counting large models.

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 opening purpose and the usage sentence are front-loaded and earn their place. However, the 17-value model list is duplicated verbatim from a schema that already covers it at 100%, roughly tripling the length for zero added information.

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 one-parameter, non-destructive read with no output schema, purpose, trigger, and scope are all covered. Only edge cases (does the count include soft-deleted or draft documents) are left unexplained.

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% and the single `model` parameter is fully documented in-schema. The description's enumeration of valid models adds no meaning beyond the schema text, so the baseline of 3 applies.

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 ('Return the exact total count of records') scoped to a model type within the account. The 'exact total' framing implicitly separates it from the numerous search_*/list_* siblings, though none are named explicitly.

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?

'Use this to answer "how many X do I have?" questions' gives a concrete trigger condition. It stops short of naming an alternative (e.g. use search_invoices when you also need the rows) or stating exclusions, so it's clear context rather than a full routing rule.

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