grep_all_coursesSearch all active Canvas courses by keyword in one call. Use it when the course is unknown; prefer course-specific search when the course is known.
Search every active course by keyword in one call. Read-only but uses many API calls; prefer search_course_content when you know the course.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of items to return. Smaller is faster. | |
| query | Yes | Search text. |
Changes observed during successful MCP inspections.
v1.1.3Input schema / properties / limit / descriptionPrevious value: -"Max items to return"New value: +"Maximum number of items to return. Smaller is faster."Input schema / properties / query / descriptionAdded value: +"Search text."v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds one genuinely useful behavioral fact — 'uses many API calls' — signaling cost/latency for a fan-out search. However, it says nothing about pagination, result caps, or what the 'limit' actually bounds across courses, which is the main behavioral unknown for a broad search. Some added value, but not rich.
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 short sentences, zero waste, with the core capability front-loaded and the routing advice second. Every sentence earns its place.
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 two-parameter read-only search with no output schema, the definition covers purpose, scope, cost, and the alternative. The main residual gap is that it doesn't indicate what results look like (course-level matches vs. content snippets) or how 'limit' interacts with cross-course search, but nothing blocks a correct call.
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% and both parameters are documented ('Search text.', 'Maximum number of items to return. Smaller is faster.'). The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.
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+resource+scope: 'Search every active course by keyword in one call'. It also implicitly distinguishes itself from the narrower per-course alternative, so an agent can tell what it does without opening the 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?
Explicitly names the alternative (search_course_content) and the exact condition that selects it ('when you know the course'). This is the when/when-not pattern in miniature.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.