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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower, and the description still adds two real behavioral facts: uniqueness of the primary profile and the 404 error when no primary is configured. That error contract is exactly the kind of detail structured fields do not carry.

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 sentence, front-loaded with what is returned, followed by the cardinality constraint and the error case. No filler, no restatement of the title, and each clause earns its place.

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 zero-parameter read with no output schema, the definition covers identity, cardinality, and the failure mode, which is enough to call it correctly. It does not sketch what fields the returned profile exposes, which is a minor gap given no output schema exists to carry that information.

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?

The tool takes zero parameters, so the baseline applies and nothing needs explaining on the input side. The description correctly spends no words on parameters and instead invests in the resource semantics.

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 gives a specific verb and resource ("Returns the workspace's active (primary) Ideal Customer Profile") and defines what 'primary' means in domain terms plus its cardinality ("at most one is primary"). It does not explicitly name get_icp or set_primary_icp as the alternatives, so it stops just short of full sibling differentiation.

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 use case is implied — retrieve the profile the workspace currently targets — but there is no explicit statement of when to call this versus get_icp (lookup a specific profile) or set_primary_icp (change it). The 404-on-unset note is a useful signal about the empty state but is not routing guidance.

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