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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false), so the description's real contribution is the atomicity guarantee ('All the ideas in one call are saved together, or none are') and the explicit 'No AI, the text is stored verbatim'. It also discloses the permission gate on author. It does not discuss failure modes for oversized content or rate limits, which keeps it off 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?

One dense paragraph, front-loaded with the purpose before the routing guidance. Nearly every sentence carries non-derivable information (atomicity, author scoping, references-vs-content), though the closing tags sentence and the audience caveat partially restate schema text and 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 2-parameter tool with a nested idea object and no output schema, the description covers the things an agent would otherwise get wrong: workspace selection order, dedupe via list_ideas, verbatim/no-AI storage, cross-idea atomicity, and where source material belongs. What it lacks (return shape, tag-creation failure reply) is already covered by the schema's parameter descriptions.

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%, so baseline is 3, but the description adds meaning the schema does not: author is scoped to the whole call ('one author per call, applied to every idea in it'), and the content/references split is given a rationale ('references are stored alongside it and carried over to the post when the idea is drafted' vs the idea text being what gets drafted). Tags' persistence through drafting is likewise stated beyond the schema's matching rules.

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 ('Save one or more ideas to the Ideas tab of the active workspace') and immediately disambiguates what an idea is ('thoughts that are not posts yet'). It explicitly contrasts with the nearest sibling, save_draft, so an agent can pick between them without opening a 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?

Names the alternative ('Use this, not save_draft, when moving a backlog of ideas in from another tool') plus the prerequisite ordering: call select_workspace first to pick the client, and list_ideas to avoid duplicates. The author case ('When the ideas belong to a teammate, pass their name as author') is an additional conditional rule with its own trigger.

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