Read a course file's text

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's main behavioral value is confirming it's non-destructive reading. The description adds key behavioral context: it can process multiple document formats (PDF, .docx, .pptx, .xlsx, HTML, plain text) and it extracts text from those files. It does not mention file size limits or supported character encodings, but for a file-read tool with good annotation coverage, this is sufficient. No contradiction with annotations.

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?

Three sentences, zero wasted words. The first sentence states what the tool does and its supported formats. The second sentence gives concrete use cases. The third sentence tells the agent where to find the required parameter value. Every sentence serves a distinct purpose, and the most actionable information is 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?

Given the tool's moderate complexity (2 params, no nested objects, no output schema), the description covers purpose, usage, and parameter source well. It does not explain expected return format (the extracted text and possibly metadata), but since no output schema exists, the agent would benefit from that. However, by listing file formats and extraction behavior, the agent can reasonably infer the output shape. A minor gap given the tool's simplicity.

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 100%, so both parameters (file_id, max_chars) are already documented in the schema. The description adds value by specifying that file_id comes from specific sources (canvas_list_files or module item's content_id), which clarifies the data dependency. The max_chars parameter is not mentioned in the description, but since the schema already provides a clear description, description coverage is acceptable.

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 uses clear verb-resource pairing: 'Download a Canvas file and extract its text', immediately stating the core purpose. It lists supported formats (PDF, Word, etc.) and concrete use cases (syllabi, lecture slides, handouts), leaving no ambiguity. Among siblings like canvas_get_file_link (which just returns a URL) and canvas_read_syllabus (which reads a specific syllabus), this tool is distinctly positioned as the generic text-extraction tool for any 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?

The description explicitly tells the agent when to use this tool ('Use this to read syllabi, lecture slides, and handouts') and tells it where to get the file_id ('file_id comes from canvas_list_files or a module item's content_id'), which is critical since the agent might otherwise not know how to obtain a valid file_id. It does not provide when-not-to-use guidance, but for a read-only extraction tool with clear purpose, the positive guidance suffices.

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