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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is largely covered by structured data. The description does add real behavioral content beyond them: results are returned as path:line: text and include held (uncommitted) changes, which an agent could not know otherwise. However, it says nothing about result limits, ordering, case sensitivity, or how the destructiveHint=true annotation squares with a read-only search.

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?

It is short with no filler, but it is a sentence fragment with no main clause, which makes it read as garbled rather than terse. The opening clause about site largely duplicates the schema description, and the substantive payload (result format, path narrowing) is buried after it.

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 four parameters, 25% schema coverage, and no output schema, the description carries most of the explanatory burden and does not meet it. The result format is covered, but the theme identifier convention and query matching semantics – the two things an agent most needs to call this correctly – are absent.

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 only 25% – just the site parameter is documented in the schema. The description repeats that datum ("named in site") rather than adding to it, and only partially clarifies path as a narrowing filter. The theme and query parameters, including whether query is a substring, a regex, or case-insensitive, are left entirely undefined in both places.

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 fragment "Where a string appears in the theme, held changes included, as path:line: text" does convey a grep-like content search over theme files, and it identifies the resource and output shape. But there is no main verb and no explicit statement that this tool searches rather than lists or reads, so the agent has to infer the intent from the name. It also never distinguishes itself from siblings like search_docs, list_theme_files, or read_theme_file.

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?

"narrow with a path" is the only usage-ish cue, telling the agent that path is a filter. There is no statement of when to choose this over read_theme_file or list_theme_files, no preconditions, and no note on whether the theme must be built or whether revisions are covered. The agent gets no routing guidance at all.

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