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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true. The description adds genuinely useful behavior beyond that: the URL is signed and access-bearing, so it must only be handed to an entitled reader, plus the precondition on transcription.

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 short sentences, each carrying distinct information (return value, precondition, security caveat), with the important scoping constraint near the front. The trailing raw endpoint path is mildly redundant but still informative.

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?

With no output schema, the description correctly explains the return value and adds the precondition and a sharing caveat. It omits whether the signed URL expires or how long it remains valid, which would be the remaining gap for a credential-bearing return value.

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 the single parameter is fully documented in the schema (session uuid from lessonspace_list_sessions). The description adds only that session appears in the URL path, 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 precisely what the tool returns: a signed download URL for a session's transcript. It implicitly distinguishes itself from the sibling lessonspace_get_session_recording by naming the transcript resource, though it never names that sibling explicitly.

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 a clear precondition for use: transcription must have been switched on at launch (transcribe=true). It does not name alternative tools or describe what to do when the precondition fails, so it stops short of full routing guidance.

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