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

Annotations declare readOnlyHint and non-destructive, so safety is covered. The description adds important context not in annotations: followers see their own selections while the owner sees the union, and it explicitly excludes collector health/delivery timing. This is meaningful behavioral disclosure beyond 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 focused sentences, front-loaded with the core purpose, then usage guidance, then scope clarification. No filler; every sentence adds value.

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?

An output schema exists so return values needn't be explained. For a read-only 1-param tool, the description covers purpose, format routing, visibility semantics (follower vs owner), and explicit non-scope (health/timing). Nothing an agent needs to invoke it correctly is missing.

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?

One parameter (streamId) with 0% schema description coverage. The description implies the stream must be 'accessible' and owned/followed, which adds usage context for the ID, though it doesn't detail format constraints. With only one param and no explicit schema description, the description partially compensates.

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?

Specific verb ('Read') and resource ('custom-target values') with examples of what those values are (accounts, channels, repositories, tracking criteria). Distinguishes itself from sibling get_stream by explicitly routing to it for target-format instructions.

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?

Clear usage context ('Confirms saved selections, not collector health or delivery timing') and names get_stream for format guidance. Lacks explicit when-not-to-use (e.g., when to prefer patch_stream_custom_targets or set_stream_custom_targets), but the routing to get_stream covers the main ambiguity.

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