List writing pieces

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: result ordering, what the response contains ('pieces and count'), and that the corpus is local drafts rather than fetched posts. It doesn't cover truncation behavior when limit caps the list, which keeps it from 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?

Four short sentences, each doing distinct work: what is listed, how to use it relative to siblings, what comes back, and what the list is not. Scope and routing information is front-loaded with no filler.

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?

With no output schema, the description compensates by stating the return shape ('pieces and count') and ordering. For a three-optional-param read tool with full annotations this is close to sufficient; only the behavior at the limit boundary and whether results are paginated is left unaddressed.

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 100%, so all three parameters are already documented including the kind enum and limit bounds, making 3 the baseline. The description does add a little by framing the optionality as 'filtered by kind or source item', which maps yoink_id to a source-item concept, but it adds no format or interaction detail the schema lacks.

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+resource ('List saved tweet, thread and blog drafts') plus ordering ('newest first') and optional filters. It explicitly separates this tool from list_scripts (video-script versions) and get_writing_piece (single-record retrieval), so an agent can route correctly without opening the 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 a concrete use case ('find a piece ID for get_writing_piece') and names the sibling alternative with the condition that selects it ('use list_scripts for video-script versions'). The closing sentence also defines a scope boundary, ruling out fetched social/publishing posts.

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