mnemosyne_todo_categories

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

Annotation Contradiction: annotations declare readOnlyHint=true, yet the description describes mutating operations ('create one, rename or recolour one, remove an empty one') and explicitly states 'Scope todo:write'. The title 'List To-do lists' also implies a read-only listing while the description describes workspace mutation. Because the description's semantic content directly contradicts the annotation's safety signal, the score is forced to 1 despite the description itself being behaviorally rich.

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 description is front-loaded with purpose and every sentence carries load-bearing information: operation set, sibling discriminator, two refusal conditions, special status of original lists, runtime requirement, and scope. It is dense rather than bloated, though it reads as one long paragraph — a bullet list of the refusals would aid scannability. No sentence is wasted.

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 mutating tool with one nested parameter, no output schema, and minimal annotations, the description covers the operations, the sibling alternative, both refusal conditions, the immutable original lists, runtime prerequisites, and required scope. The only substantive gap is the readOnlyHint contradiction, which muddies the reliability of the overall signal; otherwise the description is thorough enough for an agent to invoke it correctly.

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 the ops array and its fields are already fully documented in the schema (baseline 3). The description adds meaning beyond the schema by explaining refusal behavior at actual call time: the agent is told how many tasks block a removal, must move them first, and the app will not choose a destination on the user's behalf — operational detail the schema lacks. This added value justifies a 4 rather than a 3.

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?

The description opens with a specific verb+resource ('Manage the lists of the user's To-do backlog') and enumerates the exact operation set: create, rename or recolour, remove an empty one. It also distinguishes itself from the most confusable sibling (mnemosyne_todo_update) by naming it directly and explaining the difference: shape of a workspace vs. work in it. An agent can select this tool correctly 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?

The sibling routing is explicit: mnemosyne_todo_update is named as the alternative, with the selection rule being whether the change alters workspace shape or work content. The two refusals serve as when-not guidance ('A list that still holds tasks is never removed', 'The three original lists can be renamed, never removed'), and the runtime caveat (daemon on dev install vs. app running on npm install) states a prerequisite condition clearly.

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