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

Annotations already establish read-only, but the description goes well beyond them: it discloses that a key with nothing stored is null rather than absent, that `include_editable` executes the theme's Customizer code and is therefore slower, and that the server marks the tool read-only so it runs without a confirmation round-trip. Those are exactly the traits that change how an agent sequences and cost-weights the call.

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 verb and return shape, then parameters, alternatives, and execution behavior in a sensible order with no filler. It is densely packed — the first sentence carries a parenthetical gloss and the last sentence adds provenance — so it reads slightly crowded rather than crisp, but nothing is redundant.

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?

There is no output schema, so the description carries the return-value burden and does so by naming `{ stylesheet, mods }` and the `editable` entry shape. With only three optional parameters, an explicit performance caveat, and sibling routing all covered, an agent has everything needed to invoke it correctly.

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 is 3, but the description adds real meaning the schema lacks: the `foo[bar]` bracket syntax for reading inside a mod, the null-means-default semantics, and the full shape of the `editable` payload ({ key, default, label, control_type, choices }). The `site_id` parameter is left entirely to its enum/description, which keeps it 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?

States a specific verb and resource — reads the active theme's stored theme mods — and immediately glosses the term (Customizer values classic themes keep: logo, colours, layout), which an agent can use to decide relevance. It also declares the return shape `{ stylesheet, mods }` and implicitly scopes itself to classic themes versus block-theme global styles.

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?

Explicitly routes one adjacent need: 'Additional CSS is read with wp_get_custom_css', and names the mutating siblings (wp_update_theme_mod, wp_delete_theme_mod) so the agent knows this tool is the read counterpart. It gives the condition for the expensive flag ('include_editable: true ... it is slower') but never states an explicit when-not or names the block-theme alternative (wp_get_global_styles) outright.

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