solidtime_project_members

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

Annotations already disclose destructive, idempotent and non-read-only behavior, so the bar is lower. The description still adds real non-obvious context: "Rate fields can reprice past entries" warns that mutating a billable rate retroactively affects historical time entries, which is exactly the kind of side effect an agent needs. It stops short of saying what a delete destroys (cascading removal of the membership?) or whether list paginates.

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?

It is short and front-loads the resource, with zero filler, but the telegraphic fragment style ("action list, create, update, delete") trades away clarity. Brevity here reads as under-specification rather than discipline.

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 destructive four-action CRUD tool with seven parameters, one required discriminator, no output schema and thin schema coverage, the description is too thin. It never maps parameters to actions or explains the delete consequence, which is the highest-risk gap given destructiveHint=true.

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 only 29%, so the description must compensate, and it largely does not. It touches billable_rate (repricing) and confirm (writes need confirm), but the three identifiers (member_id, project_id, project_member_id) are never explained, leaving the agent to guess which ID each action expects.

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 names the resource ("Project members") and enumerates the four supported actions, so the surface area is visible. But it never states what an action actually does (e.g. what "update" changes or what "list" returns), and it does not distinguish this CRUD wrapper from similarly named siblings such as solidtime_members_list or solidtime_projects_list.

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?

There is no guidance on when to pick this tool over siblings, and no per-action selection criteria (which identifier applies to which action). The only usage-like instruction is "Writes need confirm," which is a prerequisite for the confirm parameter rather than a when-to-use rule.

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