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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds value by disclosing the full response surface, the state/owner/waiver semantics, and an authorization condition ('Any caller who can read the project'); 'records nothing' mildly extends readOnlyHint by implying no audit trace.

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 core verb+resource, then a dense enumeration of returned fields, then two terse constraints. The middle clause is long but every item earns its place given there is no output schema; it could be split for readability.

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?

With no output schema, enumerating the return contents (criterion results, waivers, gaps, readiness flag, enforcement mode, last check) is essential and done well. A read-only tool with annotations and an access note is largely complete; missing only edge cases (unknown project, empty readiness) which are minor here.

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 50%: the 'transition' enum is fully documented in the schema, and projectId is undocumented but self-evident. The description's '(or archived)' echoes the transition meaning but adds no syntax or constraint beyond what the schema already provides, 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?

States a specific verb ('Read') and resource ('one project's live readiness to be completed or archived') and enumerates the returned content, so an agent knows exactly what it gets. It does not explicitly contrast with siblings like run_readiness_check or list_readiness_criteria, so it falls short of full sibling differentiation.

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 implied by 'live readiness' and 'Changes nothing and records nothing', which signals a read versus a compute/run, but no explicit when-to-use, when-not, or named alternative (e.g. run_readiness_check) is given. The access condition ('Any caller who can read the project') is the only guard rail.

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