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

The description discloses the process (re-hash, bind ref_sha, match), a negative (does not publish), a failure condition, and the approval workflow. The annotations already indicate it is a write and destructive (readOnlyHint=false, destructiveHint=true), but the description adds value by explaining the operation's sequence and prerequisites. It does not explicitly mention that the operation is destructive, but that is covered by 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?

The description is well-structured: the main action is front-loaded, followed by usage condition, failure condition, and a bracketed approval note. It is compact but contains necessary operational details. The approval note is somewhat lengthy but is actionable and relevant. No unnecessary repetition.

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 tool with 4 parameters, no output schema, and destructive/write annotations, the description covers purpose, usage timing, failure conditions, and approval requirements. It explains what the tool does and when to call it. It does not detail return values or side effects on other entities, but the lack of output schema and the given context make it reasonably complete.

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 coverage is 100% for all 4 parameters, each with descriptions. The description does not significantly expand on parameter semantics beyond what the schema provides—it mentions 're-hash' and 'bind ref_sha' which relate to 'sha' and the general process, but does not add syntax or format details for parameters like 'item_id' or 'companyId'. The baseline of 3 is appropriate given full schema coverage.

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 a specific action: 'Refresh a waiting words-ready card from its save PR tip' and lists the sub-steps (re-hash, bind ref_sha, match card). It differentiates from publish tools via 'Does not Publish' and provides a precondition ('Fails if the PR is not this card's save branch'). However, it relies on domain jargon ('waiting words-ready', 'blessed body') that may be ambiguous without further context, and it does not explicitly name sibling alternatives beyond the publish distinction.

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?

Clear when-to-use guidance is given: 'Use after the blessed body was pushed onto that PR.' It also states what it does not do ('Does not Publish') and a failure condition ('Fails if the PR is not this card's save branch'). The approval note ('Call it on the first clear ask') adds operational guidance. It does not name specific alternative tools, but the context is sufficient for an agent to decide.

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