api_get

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

Annotations already disclose readOnlyHint and openWorldHint; the description adds useful non-redundant behavior: it performs an HTTP GET, returns raw JSON, and auto-inserts the API version for /lp/ and /le/ paths. There is no contradiction with the readOnlyHint annotation.

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 sentences with no wasted words. The escape-hatch role is front-loaded, and every clause adds useful information: raw JSON, version auto-insertion, and the full-path alternative.

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 single-parameter generic GET tool with readOnly/openWorld annotations and no output schema, the description fully covers the input format, path-version behavior, and return type. The explicit 'return raw JSON' statement compensates for the missing output schema.

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?

There is only one parameter and schema description coverage is 0%, so the description must carry the burden. It defines path as a Valence API path, explains the difference between /lp/ and /le/ shorter forms versus the full /d2l/api/ form, and gives a concrete example. This goes well beyond the schema's pattern.

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 label 'Escape hatch' plus 'GET any Brightspace Valence API path and return raw JSON' clearly states the generic purpose and distinguishes it from the fifteen specialized sibling tools.

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 term 'Escape hatch' implies use when no dedicated sibling tool covers the needed endpoint, and 'any ... path' reinforces that fallback role. However, it never explicitly says to prefer specialized tools or names a specific alternative condition.

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