read_recording

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description correctly aligns. It adds useful behavioral context beyond annotations: it verifies both account identities and the source recording link, and specifies exactly what is returned (title, description, duration, dates) and what is not (playback/transcript). This enriches the agent's understanding of side effects and boundaries.

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, zero redundancy. The first sentence front-loads the purpose and prerequisites; the second covers verification, return contents, and exclusions. Every clause earns its place with actionable information. Excellent structure for an agent to parse quickly.

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?

The description covers the purpose, prerequisites, return fields, and exclusions, which is solid for a read-only tool. However, it omits behavior for offset and maxChars (likely pagination/truncation), which an agent needs to correctly invoke the tool with those parameters. No output schema means the agent relies on the description for return expectations, and while it lists fields, it doesn't describe how they are formatted or any error conditions. Adequate but with clear gaps.

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 50%: only courseId and topicId have descriptions. The description itself does not explain offset or maxChars, which are entirely undocumented in both schema and description. It adds some context by framing courseId and topicId as 'exact' identifiers from 'another tool', but fails to compensate for the two undocumented parameters. Given the low coverage, the description should have provided meaning for these, but it does not.

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 ('Read'), a precise resource ('Collegerama presentation metadata'), and narrows scope to an 'exact visible topic in an enrolled Brightspace course.' It also clarifies what is excluded ('playback and transcript contents'), which distinguishes it from list_recordings that likely returns a list. This is a distinct, well-scoped definition.

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 implies when to use this tool: when you have a specific topic ID and need metadata for that topic, and when authentication and enrollment are prerequisites. It does not name alternatives explicitly, but the 'exact visible topic' phrasing and the distinction from list_recordings provide clear context. No explicit exclusions, but the intent is evident.

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