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

Annotations only cover readOnly/openWorld; the description adds the non-obvious behaviors that matter — server-side scanning, exact:false for very large collections, lower-bound counts, and the accumulate-cursor contract. This is exactly the context an agent needs to interpret a non-exact result.

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?

Purpose and the cursor caveat are front-loaded, and every sentence earns its place. However, the second and third sentences are run-ons with missing spaces after commas ('cursor,call again'), which slightly hurts readability.

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?

With an output schema present, the description needn't cover return shape, and it still warns about exact:false, which the schema alone may not disambiguate. Nothing needed to call this correctly is missing.

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 schema already documents repo/cursor/collection. The description nonetheless adds real semantic value: the new count covers records AFTER the cursor and must be added to the previous total, which is the key usage contract for cursor.

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+resource+scope: 'Count the total records in an account's collection', with a concrete example. It is clearly distinguishable from siblings like list_records (returns rows) and count_repos_by_collection (counts repos, not 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?

Explains the operative path: use it instead of paging manually, and when a capped result arrives, call again with the cursor and ADD the counts. It gives clear context for the cursor workflow but never names an alternative tool or when not to use this one.

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