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

Annotations only declare readOnly=false, destructive=false, idempotent=true, openWorld=true; the description adds substantial context beyond that: conflicts leave a merge open and the site held from going live, <<<<<<< markers appear in named files, resolving the last file commits and lands the merge, and success requires the theme to validate. Admin-only authorization is also disclosed. This is exactly the behavioral detail annotations cannot 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?

Every clause carries information (prereqs, merge behavior, conflict path, alternatives, auth), and the scope constraint is front-loaded. But it is one dense run-on paragraph with garbled fragments ('then render_page and walk the release notes' Check', 'no validator error; in a theme that builds, built') that force re-reading. Information density is high; readability is not.

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 multi-stage, stateful operation with no output schema, the description covers preconditions, success criteria, the conflicted branch, and escape hatches. What it omits is the result shape after a successful merge (e.g., what state or files are returned), which an agent may want before chaining calls.

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 50%: 'site' is documented in the schema, 'theme' is bare. The description compensates by anchoring 'site' to list_sites naming and, critically, telling the agent the theme value comes from the `update` field of list_themes. That is real meaning added for the undocumented parameter.

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?

States a concrete verb and resource: bringing the bundled theme's newer release in via a three-way merge over the site's own edits. It also distinguishes itself from plan_theme_update (prerequisite) and resolve_theme_update (conflict alternative), so the agent can tell what it is not. The convoluted phrasing ('in a theme that builds, built') keeps it short of a 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?

Explicit prerequisite ordering: run only 'after plan_theme_update and the person's go,' plus the admin-only restriction. It names the alternative path (resolve_theme_update settles conflicts by side or takes the update back) and when to use it. No explicit statement of when this tool should be avoided entirely, which is the only gap.

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