scf_get_change_cursor

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

Annotations only mark readOnlyHint; the description adds operational context: it is a cheap probe, requires only viewer role, and returns two values (timestamp and row count). It also discloses the intended polling pattern, which annotations cannot convey. No contradiction with annotations.

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?

Two dense sentences front-load the purpose, cost, and auth level before giving the polling instruction. Every clause earns its place; no filler.

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 read-only probe with no output schema, the description covers purpose, return values, role requirement, and the exact usage pattern. The only mild ambiguity is 'the pair you last saw,' but the preceding clause identifies the pair as timestamp and row count.

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 description coverage is 100%, and the org_id schema already explains it is an Organization UUID from scf_list_organizations. The tool description only restates 'for one organization' and adds no parameter-level detail beyond the schema, so the baseline 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?

Description opens with 'Cheap has-anything-changed probe' and specifies it returns 'newest audit timestamp and row count for one organization', giving a concrete verb, resource, and output. The 'poll this before re-pulling the audit log' line distinguishes it from the audit-log fetching sibling without ambiguity.

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?

Explicitly instructs when to call: 'poll this before re-pulling the audit log' and how to use results: 'Compare with the pair you last saw.' It also implies the alternative (full audit log fetch) and frames this as the cheap pre-check, so an agent knows when to choose it.

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