project_modify_project_principals

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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=true, so the safety profile is covered. The description adds nothing beyond that: it doesn't say that removal is possible, that syncPrincipals triggers external IdP synchronization, or that validatePrincipals enforces a 20-principal limit — behaviorally meaningful facts that only appear buried in the schema.

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 lines where one would do — the first sentence is repeated verbatim and expanded only with 'by id'. It is front-loaded and short, but the duplication wastes the limited space that could have conveyed what actually gets modified.

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 mutation tool with five parameters, nested principal objects, optional sync/validate flags and no output schema, the description is insufficient: an agent gets no signal about the effect of removal, the IdP synchronization side effect, or the principal-count/validation constraints. Only the endpoint path hints at semantics.

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 80%, so the schema itself documents id, body.modify, body.remove, apiVersion and validatePrincipals adequately. The description contributes no extra parameter meaning, which is acceptable but not additive; baseline 3 applies for high-coverage schemas.

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 ('Modifies principals assigned to a project') plus the underlying endpoint, so an agent can tell this is a principal-mutation tool on a project. It does not differentiate from the close sibling project_sync_projects_principals, nor does it say that 'modify' here means add/remove/role-change, which the schema reveals only indirectly.

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?

No when-to-use guidance at all: no mention of alternatives, prerequisites, or the fact that a separate sync_principals operation exists. The agent must infer everything from the tool name and the request body.

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