compute.list_projects

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

The readOnlyHint annotation already establishes this is a safe read, so the description's contribution is the content preview ('entrypoint, environment and per-node paths'), which tells an agent what information it will get back. It does not disclose scoping (all projects vs. workspace-filtered), ordering, or pagination behavior, which would be the extra value beyond annotations.

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 short sentence with no wasted words, and the resource is front-loaded. The trailing qualifier ('with entrypoint, environment and per-node paths') is slightly compressed and reads ambiguously, but it is not padding.

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 trivial no-parameter read tool with readOnlyHint and no output schema, the description is nearly sufficient: it implies safety, hints at return content, and needs no argument documentation. The only shortfall is that, absent an output schema, it does not say whether results are scoped or truncated.

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 there is nothing for the description to disambiguate; the baseline for a no-arg tool applies. The description does not need to compensate for any schema gap.

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 a specific verb ('List') and resource ('research projects') and even previews the fields returned (entrypoint, environment, per-node paths). It is clearly distinguishable from sibling list tools such as compute_list_environments and compute_list_nodes by resource, though it never explicitly contrasts them.

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?

Usage is only implied by the verb: an agent can infer this is the discovery call for projects, but there is no statement of when to prefer it over compute_sync_project, compute_push_project, or compute_inspect_* siblings, and no preconditions or exclusions are given.

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