find_text

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

No annotations are provided, so the description carries the full behavioral burden. It discloses important non-obvious behaviors: matches are against displayed text rather than raw XML, regex is guarded against catastrophic backtracking, and results are formatted as addresses for other tools. It does not mention how include_notes or scope affect matching, which is a notable gap, but the core behavior is transparent.

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?

Four sentences, each carrying essential information: purpose and output shape, regex behavior, displayed-text semantics, and routing to the graphics pack. No filler or redundancy, and the most decision-relevant details are front-loaded.

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?

The output schema exists, so return values are covered, and the description covers many behavioral quirks. However, with five parameters, zero schema descriptions, and no annotations, leaving scope and include_notes undefined is a significant completeness gap. An agent could call the tool incorrectly by not realizing notes are included by default or not understanding what scope controls.

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 description coverage is 0%, so the description must compensate for all five parameters. It explains regex behavior and implies query semantics, but it does not explain scope, include_notes, or file_path expectations. The include_notes parameter is especially relevant because it changes what 'the deck's text' includes, yet the description is silent about it.

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 description opens with a specific verb and resource ('Search the deck's text') and states exactly what it returns: every match with slide index, shape id, paragraph index, and character offsets. This makes it easy to distinguish from sibling tools like get_text or search_and_replace without needing to inspect their schemas.

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?

The description gives strong context clues for when to use this tool: it produces addresses that format_text and apply_edits consume, and it explicitly routes formatting-aware replacement to the graphics pack via enable_tools. It does not explicitly contrast with search_and_replace, but the intended workflow is reasonably clear.

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