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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description rightly spends its words on the returned bundle instead. The note 'step agents (empty = random of the role)' is genuinely additive behavioral context that is not visible anywhere else. It falls short of disclosing not-found behavior or the both/neither-identifier case.

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?

A single front-loaded sentence starting with the read marker and the core resource, then the lookup keys, then the payload contents in priority order. The field enumeration is long but each item is informative; no filler sentences.

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 no output schema, the description does useful work listing the returned sub-structures. But with zero required parameters in the schema, the resolution logic (one of two optional identifiers) is the main thing an agent needs clarified and the description leaves it implicit.

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%, so the description must compensate. It names both parameters verbatim and frames them as alternative lookup keys, which is real added meaning. However it omits the format/type distinction (integer vs UUID string), whether the two are mutually exclusive, and what happens when both or neither are passed.

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 (retrieve one AI Office scenario) and enumerates what the record contains (steps, dependencies, keywords, targets, AI accounts, step agents, settings). The 'One' vs the sibling list_agent_office_plans is implied rather than named, so sibling differentiation is inferential rather than explicit.

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 '[read]' prefix and 'by agent_office_plan_id or agent_office_plan_uuid' hint at the single-record lookup context, but there is no explicit when-to-use guidance, no direction to list_agent_office_plans when the ID is unknown, and no rule for what to do when neither identifier is supplied.

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