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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false and idempotentHint=false; the description goes beyond that by stating that omitted fields are preserved (merge semantics) and by spelling out the return shape { ideaId, updatedFields, setup, briefReady } where no output schema exists. It stops short of covering failure behavior or the dependency between conversionMode='external_url' and externalDestinationUrl.

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 behavior-defining sentence is front-loaded, and the Args/Returns block structure makes scanning easy. The long comma-separated field dump is somewhat redundant with the schema property names and costs a few lines that could be trimmed.

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 16-parameter mutation tool with no output schema, the description does well to supply the return shape and merge semantics. It is still incomplete on conditional requirements (externalDestinationUrl when conversionMode='external_url'), on what 'setup' and 'briefReady' mean, and on whether saving triggers validation or downstream generation.

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 0% across 16 parameters, so the description must compensate. It enumerates every field name and restates the two enum constraints that already live in the schema, but adds real meaning only via "all optional, at least one required" and the required ideaId framing; individual field intent (e.g., what notesToAvoid vs currentAlternative mean) is left to the reader.

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?

"Save one or more brief fields on an idea" gives a specific verb and resource, and the follow-up sentence clarifies the partial-update scope. It does not name or contrast with the likely sibling (idealaunch_draft_brief) or idealaunch_create_idea, so an agent must infer the boundary between drafting and saving.

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 the partial-update sentence and the "at least one required" rule, which is a genuine calling constraint not expressed in the schema. However, there is no explicit when-to-use guidance, no exclusion (e.g., "use draft_brief to generate fields from scratch"), and no prerequisites such as required permissions or an existing idea.

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