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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds genuinely new behavior: result ordering (newest first), the keyset pagination model, and the fact that agent connections get enriched rows containing the user's role, the token's permission, the plan, and the org. It does not mention rate limits or result caps beyond the schema's limit maximum.

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?

Front-loaded with the action and the permission tag, then the scope rules, then the downstream usage hint — a sensible order. The middle sentence is dense, packing three credential cases and a four-item parenthetical into one run, which costs a little readability but no sentence is wasted.

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 two-parameter, read-only list tool with no output schema, the description carries the needed weight: it explains what population is returned per credential type, the ordering, and the pagination model, plus a hint on consuming the ids. The main residual gap is the general response shape (field names of the base project object), which is only described for the agent-connection case.

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 100%, so both `limit` and `cursor` are already fully documented, and the baseline is 3. The phrase "keyset paged" reinforces the cursor's meaning and "newest first" explains what the ordering is keyed on, but no additional format or edge-case detail is added beyond the schema.

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+resource ("List projects") and immediately qualifies scope by credential type: org key, project key, or agent connection. That scoping makes it unmistakable against siblings like create_project or list_targets, and the "newest first (keyset paged)" clause pins down ordering.

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?

Gives clear context on what this returns for each kind of calling key, and explicitly tells the agent to feed one of the returned ids as `projectId` to endpoints that need it. It stops short of naming when NOT to use it or pointing at a sibling alternative (e.g. when to prefer whoami for identity resolution), so it is clear context without exclusions.

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