Update idea

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: partial-update semantics ('Omitted fields stay as they are') clarify that unspecified fields are preserved rather than nulled. It says nothing about required permissions, irreversibility, or the special clearing behavior the schema mentions for some fields.

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 short sentences, front-loaded with the core action and the partial-update rule. Slightly clipped by the trailing 'Returns the updated record', which restates information already available in the output schema.

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?

The output schema exists, so the description is not obligated to explain return values, and the patch semantics are covered. But for an 8-parameter mutation tool at 38% schema coverage, the definition omits field-level guidance and the note that some fields (e.g. tags) are replaced wholesale rather than merged, leaving real gaps.

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 38% for 8 parameters, so the description carries the burden of compensating and does not: it never enumerates the updatable fields (title, domain, status, insight, problem, assumptions), so field-level meaning is missing. The only useful addition is the generic 'omitted fields stay' rule, which does not resolve which fields can be set or how to clear them.

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 ('Change one or more fields of an existing idea'), which an agent can immediately distinguish from the read siblings (get_idea, list_ideas) and the create sibling (store_idea). It does not name those siblings explicitly, so it stops short of full 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?

The wording implies the appropriate context (modifying an already-existing idea), and the PATCH-style contract signals that this is the tool for partial edits rather than recreate-and-replace. However, it never names an alternative or states an exclusion, so the routing guidance is only implied.

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