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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true), so the bar is lower, yet the description still adds real context: a domain restriction on the status enum and an optimistic-concurrency guard that prevents clobbering concurrent edits. It does not explain the revision-mismatch failure behavior or whether unspecified fields are preserved, which keeps it short of a 5.

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?

Three dense sentences, front-loaded with the mutability scope and the promote_idea exclusion before the concurrency note. Slightly over-packed and the inline enum recap repeats schema data, plus minor typographic noise ("here , use"), but nothing is wasted or buried.

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 no-output-schema mutation tool, the description covers the mutable surface, the forbidden transition, the sibling route, and the concurrency contract an agent needs to call it safely. The only gaps are post-mismatch behavior and partial-update semantics, which are secondary given the destructiveHint already flags mutation risk.

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 only 50%, so the description must carry weight — and it does for status (enumerates the four legal values), projectId ("file it to a project"), and expectedUpdateRevision (explains it is a concurrency token taken from get_idea, which goes beyond the schema's terse "Optimistic-concurrency guard"). ideaId and description are left implicit, hence a 4 rather than 5.

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 and resource ("Update an idea") and then enumerates exactly what is mutable: title, detail, project filing, and status. It explicitly carves out the one status value it does not handle and names the sibling that does, so an agent can distinguish it from promote_idea without opening either schema.

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 an explicit negative case with a named alternative ("PROMOTED is NOT settable here, use promote_idea") and states the condition under which expectedUpdateRevision should be supplied (concurrent-edit protection, value sourced from get_idea). This is precisely the when/when-not/alternative routing the dimension wants.

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