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

Annotations already declare readOnly=false, destructive=false, idempotent=false, openWorld=false, so the safety profile is covered. The description adds real value beyond that: append position under existing notes, project-wide visibility of the content, a content-validation rejection rule for monetary amounts, and a per-call cap of 40 notes. It does not state whether a retry would duplicate notes, though 'below what is already there' hints at non-idempotent appends.

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 action and placement, then visibility and validation constraints, then the batch limit. No sentence is redundant and nothing is buried.

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 three-parameter write tool with a fully described schema and no output schema, the description covers behavior, visibility, validation, and batch limits well. The only gaps are the return value (unspecified, and no output schema exists) and the id-vs-name parameter relationship.

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 (groups, projectId, projectName) are already documented in the schema, making 3 the baseline. The description reinforces the column/note structure and the content restriction on note strings, but adds nothing about whether projectId and projectName are alternatives or how partial name matching resolves.

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 gives a specific verb and resource ('Adds notes to a project's shared board') plus placement semantics ('in titled columns, below what is already there'), which distinguishes append behavior from a read tool like fetchProjectBoard. It stops short of explicitly naming a sibling or contrasting with fetchNotes, so it is clear but not fully differentiated.

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 append/column model, and one concrete exclusion is stated ('amounts of money are refused'), which tells the agent when not to use it for financial data. There is no explicit guidance on choosing between this and the sibling read tools (fetchProjectBoard, fetchNotes) or on prerequisites for the target project.

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