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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers on real behavior: results are scoped to the caller's workspace and to projects the integration creator is a member of, and soft-deleted projects are excluded. Those access-scoping and exclusion rules are the kind of detail an agent cannot infer from the safety hints.

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?

Single dense paragraph with the critical 'no projectId needed' fact front-loaded. The return-field enumeration is long but useful given no output schema; a slight trim of the example clutter would help.

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?

There is no output schema, so the description correctly enumerates the returned fields (id, name, prefix semantics, status, deliveryTypes, counts) and pairs that with scoping and exclusion rules. Only pagination behavior is left implicit, which the schema's defaults and bounds largely cover.

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 60%, and the description compensates by restating the search semantics (case-insensitive name contains) and status values, plus explaining deliveryTypes as a multi-value set-intersection filter with example enum names. It adds little for page/limit, which remain undocumented beyond their numeric bounds.

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 and resource ('Lists projects') and immediately establishes its unique role among siblings: it is the only tool that does not require a projectId. An agent can distinguish it from stride.list_project_members or stride.whoami without opening a schema.

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 says it is the discovery tool and the mandatory first call because every other Stride tool needs a projectId. That is a precise when-to-use rule with the alternative ('nothing else gives you an id') named outright.

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