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

The annotations already establish read-only, non-destructive, closed-world behavior, and the description still adds substantial context beyond them: the null-vs-not-found semantics of {application: null}, the '***' redaction convention and why it is distinguishable from an empty value, and the fact that retrying on another surface will not bypass redaction. These are precisely the behaviors an agent needs to interpret an unexpected 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?

Three sentences, front-loaded with purpose and payload, then return semantics, then the access-failure remedy. Every sentence carries distinct information — no restatement of the name or annotation boilerplate.

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 with no output schema, the description covers the ambiguous return cases (null when invisible, '***' when redacted) that an agent would otherwise misinterpret. It stops short of describing the shape of the application object itself, but that is a minor gap given the tool's simplicity.

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 0%, but the single parameter is an integer named application_id and the description only reinforces it with 'by id,' adding no format, sourcing, or lookup guidance. That is the minimum viable level rather than genuine compensation for the coverage gap.

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 opening clause gives a specific verb and resource ('Read one application by id') and immediately scopes the payload ('with its FULL stage history'), spelling out what that log contains: entry times, actor, dwell time, typed exit reason. That detail makes it distinguishable from list-oriented siblings such as hr_list_applications without needing to name them.

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?

It gives clear negative guidance — if the record is not visible, get the correct HR role from the workspace owner rather than trying another tool, since 'every surface redacts identically.' What it does not do is state when to reach for this versus hr_list_applications or hr_get_form_response when an agent needs application data, so an explicit positive routing rule is the missing piece.

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