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

Annotations only say it's a non-destructive, non-idempotent write. The description goes well beyond that: role requirements, plan gating with the specific error the agent will see, and the conditional field rules (risk needs both probability and impact, issue keeps only impact, others neither) plus the derived score formula. Those are exactly the behavioral details structured fields don't carry.

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 dense sentences, front-loaded with the action, then permissions, then field rules, then plan gating. Every clause carries information; nothing is padded or restated from the title.

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 10-parameter mutation with no output schema, it covers permissions, plan limits, enum values, and the tricky conditional fields well. It leaves ownerId, response, and description unexplained, and since there is no output schema it never tells the agent what a successful call returns (e.g. the created item and its score).

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 the baseline would be 3, but the description adds genuine semantics the schema lacks: the cross-field dependency between kind and probability/impact, the 'others neither' exclusion, and the score = probability × impact derivation. The kind/status enums and dueDate format are also restated in prose for quick scanning.

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 and resource: 'Add a line to a project's RAID register.' That is unambiguous and clearly distinct from update_raid_item / delete_raid_item by verb alone. It stops short of explicitly naming those siblings as alternatives, so it lands at 4 rather than 5.

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?

It gives concrete preconditions: requires Administrator or ProjectManager role, and is Pro plan only, with the exact failure mode on Free ('a plan-limit message'). That is strong 'when this will work' guidance. It doesn't route to alternatives (e.g. list_raid_items to check existing entries, update_raid_item to change one), so not a 5.

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