get_access_history

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

No annotations are present, so the description carries the full burden of conveying behavior. It clearly signals a read-only operation ('Returns...records' in the first sentence), discloses that records are 'grant/deny' entries, and highlights a behavioral quirk: identification uses ENCODEDNUM/HOTSTAMP rather than PERSONID. It could add pagination or auth details, but the core behavior is transparent enough for safe invocation.

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 sentences, no filler, and the most important behavior is front-loaded. The first sentence gives purpose and the second immediately clarifies the critical identifier limitation, earning its place without waste.

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 moderately complex tool with nine optional parameters and no output schema, the description is largely complete: it states the operation, the data kind, the filtering model, and the critical identification caveat. It leaves return-structure details unspecified, but the schema and the concise behavioral description give an agent enough to call the tool correctly.

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%, so the schema already documents all nine optional parameters. The description adds meaningful semantic context beyond the schema by explaining that ENCODEDNUM/HOTSTAMP are the identification keys used by the underlying NBAPI and that PERSONID is intentionally unsupported, which helps the agent reason about which parameters to supply.

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?

The description states a specific verb ('Returns historical access (grant/expiry) records') and a clear resource subject to filters. It also differentiates from siblings by noting this tool identifies via ENCODEDNUM/HOTSTAMP and never PERSONID, which distinguishes it from other history-returning tools like get_event_history.

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?

The description implies when to use it — when you need historical access grant/deny records with optional filters. It gives one important exclusion (do not pass PERSONID; GetAccessHistory has no PERSONID parameter), but it does not name alternative sibling tools or explicitly state when a different tool should be chosen.

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