Patch a work card

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds valuable behavior not in annotations: optimistic concurrency semantics — that expectedRevision causes refusal on stale writes and that an empty axes value clears an axis. The 'only the keys present are touched' partial-update behavior is also disclosed.

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 two dense, front-loaded sentences with zero filler. Every clause conveys load-bearing information: the operation, the concurrency model, the expectedRevision condition, and the axes clearing semantics. The schema descriptions are also concise and informative. No wasted words.

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?

The tool has 3 params (100% schema coverage), nested objects, an output schema, and clear annotations. The description, combined with the rich schema and annotations, fully covers the patch mechanics, concurrency behavior, and axis handling. It's complete for the tool's complexity. The only minor gap is it doesn't explicitly preview the output, but the output schema exists so that burden is transferred.

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 schema already documents all three parameters well. The description adds value beyond the schema: it clarifies that an empty axes value clears an axis, names the exact shape '{ name: value }' for changes.axes, and explains the concurrency-check behavior of expectedRevision beyond its schema text. This exceeds the schema-only baseline of 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 says 'Patch allowed card metadata using optimistic concurrency' — a specific verb (patch) plus resource (card metadata) plus a defining mechanism (optimistic concurrency). It clearly distinguishes itself from siblings: the schema notes status belongs to project_card_transition and body to project_card_write, and the description explains axes placement, disambiguating from project_card_write and others.

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?

Explicit guidance: 'Use expectedRevision whenever the card was read earlier' and 'Declared axes go in changes.axes'. The schema additionally directs status changes to project_card_transition and body changes to project_card_write, naming concrete alternatives. This is strong when-to-use versus alternative-tool guidance.

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