get_text

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

With no annotations, the description carries the full burden and handles it well. It discloses reading order, table cell joining, cached field text, scope semantics, include_notes behavior, and the live editing side effects including that edits stay UNSAVED until live_save and that 'force' targets the open session. This is unusually transparent about a subtle mutation risk in a tool named get_text.

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?

The description is dense but efficient, front-loading the core purpose before explaining parameters and side effects. Each clause earns its place, especially the live-mode semantics which need detail. The final sentence about rendered-appearance checks is slightly tangential but still valuable for disambiguation. It could be split into clearer sentences, but stays compact.

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?

Given the tool's complexity — 4 parameters, no annotations, subtle live-editing behavior — the description is largely complete: scope, note handling, and live modes are all covered. The output schema covers return values, so that absence is not a gap. A short callout on file_path requirements or locking edge cases would make it fully complete, but the current coverage is strong.

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, and it largely does. It explains scope values explicitly ('None for all slides, a 0-based index, {"slide_id": N}, or a list'), include_notes, and the three live modes. Only file_path is left to its obvious schema meaning, with no format or path details, preventing a 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?

The description opens with a specific verb and resource: 'Plain text of the deck in reading order.' It enumerates exactly what is included (shapes, table cells, fields) and distinguishes this from rendered-appearance concerns by pointing to the assembly-export pack. This makes the purpose unmistakable and separates it from siblings like get_presentation_view.

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 clear context for when to use the tool: retrieving plain text across any slide scope, optionally including notes. It also states a non-goal ('Rendered-appearance checks live in the assembly-export pack'), which implicitly routes agents away from using this tool for visual checks. It does not explicitly name alternative tools, but the usage context is concrete enough.

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