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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's job is to add non-obvious behavior — and it does: the all-caps warning that a created field is invisible until added to a view's columns is a critical gotcha, as is "first match in the workspace" for list-scope resolution. It also discloses the required API-key scope custom_fields:write. Slightly short of 5 only because it doesn't describe failure behavior beyond the account note inherited from the schema.

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?

Front-loaded with the action and scope semantics, and the most important warning is set apart for emphasis. It is on the long side, with some redundancy — "Keep field names plain for column headers" repeats the schema's "Do not prefix names with emoji for icons", and the options structure duplicates the nested schema.

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 9-parameter mutation tool with no output schema, the description covers auth scope, the post-create view requirement, reuse guidance, and naming conventions — enough for an agent to call it correctly and finish the job. The main residual gap is what the response returns (e.g. the new field's id), though the create-then-view workflow implies it is retrievable elsewhere.

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 already 89%, so the baseline is 3; the description earns above that by explaining the scope/scopeName interaction ("scope=workspace ignores scopeName; scope=list takes a list name (first match in the workspace)"), which the schema does not state. The options-shape paragraph largely restates the nested schema properties, which caps the score below 5.

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 opening sentence states a specific verb and resource ("Create a custom field") and immediately names the three scopes, which is exactly the axis an agent needs to disambiguate from siblings like pm_update_custom_field and pm_delete_custom_field. The type list and options handling further pin down what kind of object is produced.

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 explicit when-to-use guidance ("Reuse suitable existing fields before creating another") and a required follow-up action (create/update a view whose columns include the fields), naming the exact sibling tools pm_create_view / pm_update_view. It also explains the scope-to-scopeName mapping, which is the primary decision an agent must make at call time.

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