Extract text

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

The description usefully explains why readOnlyHint=false despite an extraction operation: with save_txt it writes <name>.txt files. It also discloses the max_chars truncation behavior per document. It stops short of covering overwrite behavior or what happens when output files already exist, which is the remaining risky surface.

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?

Two compact sentences with no filler, and the core resource statement is front-loaded. The parenthetical format list is slightly noisy but earns its place by defining scope.

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 an 8-parameter batch tool with no output schema and three mutually exclusive-looking input selectors, the description leaves too much unresolved. It never explains how input_dir, input_path, and input_paths relate, nor where output lands by default, which is the main ambiguity for correct invocation.

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 38% across 8 parameters. The description adds real meaning for max_chars (per-document cap) and save_txt (writes files), but says nothing about the input_path vs input_dir vs input_paths modes, output_path/output_dir, or overwrite — exactly the parameters an agent is most likely to misuse.

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 the resource (plain text of documents) and enumerates supported formats, plus what is returned and the optional file-writing side effect. It is clear what the tool produces, but it never distinguishes itself from siblings such as convert_document, which an agent could reasonably pick for the same job.

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?

Usage is only implied: the format list suggests 'use this when you need raw text rather than a converted document', but there is no explicit when-to-use statement, no exclusions, and no mention of convert_document or the other extraction-adjacent siblings.

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