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

Annotations already cover the read-only, non-destructive, closed-world profile, and the description adds genuinely new behavior: the empty-state response ('Empty with a note until the reference-suggest job has run'), the ordering guarantee, and the required scope. It does not say how fresh suggestions are or whether the list mutates as suggestions are accepted.

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?

Front-loaded with what the tool returns, then follow-up actions, then the empty-state caveat and auth note — a sensible ordering. It is dense but every sentence carries operational information; only the parenthetical reason-code list is slightly bloated.

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 two-optional-param read tool with an output schema and full annotation coverage, this covers the decision-relevant facts: what comes back, how to act on it, and the empty case. Only the refresh/lifecycle of suggestions after acceptance is unaddressed.

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%, with kind (enum) and limit documented in-schema, so the schema carries the parameter burden. The description adds nothing about kind or limit — the enumerated tokens it lists ('same_niche, beats_baseline...') are reason codes in the response, not inputs.

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 resource (suggested references for the account to follow), the ordering ('best first'), and the payload shape ('each with reasons [{code, evidence}]'). It is distinguishable from references_list (existing followees) though it never explicitly contrasts with references_browse or reference_search.

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 an explicit downstream workflow ('Accept with references_add {suggestionId}, dismiss with references_remove {suggestionId}') and a precondition ('Needs the read scope'), which is clear usage context. It stops short of saying when to prefer this over references_browse or reference_search when looking for candidates.

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