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

Annotations only supply readOnlyHint, and the description adds real behavioural context: retired fields are flagged, revision 0 means no fields exist yet, and the "problem" state means the field file is broken so nothing can be saved until the user fixes or removes wp-content/fabrement/fields/<file>, with an explicit instruction not to recreate the fields. That error-state guidance is exactly what annotations cannot convey.

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 core purpose and the return contents, but it then stacks several concerns (workflow ordering, template read idiom, options-page redirect, problem-state handling) plus a trailing rules line about the skill doc. Dense but each sentence carries information; minor structural sprawl.

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?

With no output schema, the description carries the full burden and does so: it enumerates the returned shape (names, meta keys, retired markers, layout, revision), documents the empty case and the broken-file case, and states the upstream/downstream workflow. Nothing needed to call it correctly is missing.

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 both parameters are already documented in the schema, including the slug pattern example and the "post" owner kind. The description only lightly reinforces this (site-wide settings are not fields of a type), so baseline 3 is appropriate.

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?

Specific verb+resource: it returns the custom fields defined for a post type, enumerating name, meta key (fab_<name>), retired flag, form layout and revision. It explicitly demarcates itself from the options-page tools ("Site-wide settings: get-options-page"), but it never mentions the near-neighbour fabrement-list-post-type-fields, leaving that ambiguity for the agent.

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 sequencing rules: call it before save-fields (because the caller needs the revision and existing fields) and before a template reads fields. It also names the read path for values (fabrement_get_field with an explicit record id, never get_post_meta) and mandates reading the fields-contract skill doc before the first call.

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