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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so 'Changes nothing' adds little. The description does add genuinely new context the annotations cannot carry: that env names are exposed but never values, and that to-dos are limited to ones only the person can do — useful for anticipating output shape and privacy boundaries.

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 front-loads the core idea ('One project in depth') then degrades into a long comma-spliced laundry list across a single sentence. Every element is informative, but the run-on structure makes the content harder to scan than a short bulleted or clause-separated form would.

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 must carry the return-value burden, and it does — it enumerates the major sections returned including next_steps ordering. The only gap is the shape of next_steps beyond 'what is left to do, in order', which is minor for a read-only tool.

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%: both `project` (id, name, or owner/name) and `workspace` (teammate workspace, defaults to your own) are fully documented in the schema. The description adds nothing about either parameter, so baseline 3 applies.

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 states the resource and scope precisely ('One project in depth') and enumerates the concrete contents (phases, env names, hosting costs, deployments, next_steps), so an agent knows this is a single-project deep read rather than a list. The verb is implicit and it does not explicitly contrast with siblings like status, diagnose, or check_repo, so differentiation is only partial.

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: an 'in depth' project overview including next_steps suggests calling it when you need the full state of one project. No alternative is named, no exclusion is given, and nothing tells the agent when to prefer status, diagnose, or deployment instead.

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