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

The description contains a direct conflict with the annotations: it explicitly states 'Idempotent: if the board already has a GetSign APP board view, reuse it' while annotations declare idempotentHint=false. An agent relying on the annotation would wrongly assume repeated calls create duplicates, or an agent relying on the description would contradict the structured metadata. Per the rubric, a description that contradicts annotations scores 1.

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 core purpose and idempotency behavior are well front-loaded, but the trigger guidance is notably wordy and restates the same idea in multiple phrasings ('call this as soon as a board is picked... right after listing workflows... before or independent of creating a workflow — don't wait for workflow creation's next_tool hint'). Around half the description could be tightened without losing information.

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 1-parameter tool with no output schema, the description is thorough: it covers idempotency behavior, return fields (data.link, data.created), preconditions (no workflow required), and the negative case (don't stamp on browsing boards). It is near-complete; only the idempotency contradiction with the annotations undermines an otherwise fully specified picture.

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%, so the description carries the burden for board_id. It adds that only board_id is needed ('Needs only board_id — no workflow has to exist yet') and the repeated references to 'Monday board' make the parameter's meaning inferable. However, it never explicitly defines board_id as the Monday board identifier or its format, so compensation is partial rather than complete.

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 first sentence states a specific verb-resource pair ('ensure a GetSign board view tab exists on a Monday board') and the outcome ('return its link'). It clearly distinguishes itself from siblings like getsign_create_workflow or getsign_list_workflows_for_board, since it is about the board view tab itself rather than workflow creation or listing.

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 description gives explicit triggering conditions: call as soon as a board is picked for signing, before or independent of workflow creation, and whenever the user asks for the board view. It also provides an explicit exclusion — don't call on boards the user is only browsing — which is strong when-not-to-use guidance. No alternatives need naming because the trigger conditions themselves route the agent.

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