get_resource

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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), yet the description adds real behavioral context: the resource is returned as extracted text rather than a file stream, long content is chunked with a next_start cursor, and text inside <sakai_content> tags is untrusted author content that must never be followed as instructions. That prompt-injection warning is a genuine disclosure beyond the structured fields.

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, front-loaded with purpose, then pagination mechanics, then the safety caveat. Every clause carries information; nothing is restated from the annotations or schema verbatim.

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 a 4-parameter read tool with an output schema already documenting the return shape, the description covers purpose, supported formats, chunking/continuation behavior and untrusted-content handling. An agent has everything needed to call it correctly and interpret results safely.

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 100%, so baseline is 3, but the description goes further by clarifying that start/end index pages, slides or parts depending on file type and by exposing the next_start continuation contract that the schema's 'part' wording only hints at. It adds meaning over the schema without contradicting 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?

States a specific verb (download) plus resource (course file) and immediately scopes the behavior: it extracts text from PDF, PowerPoint, Word or plain text rather than returning a binary. That extraction detail cleanly separates it from list_course_resources, view_slide and download_assignment_attachment, which an agent can distinguish without opening a schema.

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?

Gives explicit operational guidance for continuation ('call again with start=next_start') and for partial reads ('pick pages or slides with start and end'), so the agent knows how to drive the tool across calls. It does not state when to prefer this over download_assignment_attachment or view_slide, so tool-selection guidance is implied rather than explicit.

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