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

Annotations already declare readOnlyHint=true, so the safe-read profile is covered structurally. The description adds no behavioral context beyond that — no pagination, no ordering, no scope limits (e.g., whether inactive streams return anything) — so it earns little credit for disclosure.

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 compact sentences with the core purpose front-loaded and no filler. The endpoint-mirroring sentence is arguably redundant for an agent, keeping it just below a 5.

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 simple one-required-param read tool this is minimally adequate. Since there is no output schema, the description could have described the returned destination shape or list behavior, which it does not.

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% (the single 'stream' param is documented as a Stream UUID), so the schema carries parameter meaning. The description implies the stream parameter but adds no format or constraint detail beyond it. Baseline 3 is appropriate.

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 (List) and resource (a stream's multistream destinations), and the parenthetical clarifies what a 'destination' is, disambiguating it from unrelated list_* siblings. It stops short of naming the sibling it complements (add_destination/remove_destination), so a 4 rather than a 5.

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?

No when-to-use guidance or alternatives are given. The only positional cue is 'Mirrors GET /api/v1/streams/{stream}/destinations', which is an implementation mapping, not selection guidance. Given three sibling destination-mutating tools, an agent gets no explicit routing help.

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