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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds the embedding-based ranking and 'most similar first' ordering, which is real value. It omits whether the seed post itself is excluded from results and what happens when fewer than `limit` similar posts exist — meaningful gaps for a similarity tool.

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, front-loaded with what the tool returns and how it ranks, then the use case. No redundancy or filler.

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?

A read-only two-parameter tool with full schema coverage and no output schema; the description conveys ranking, source, and intent adequately. Missing only edge-case behavior such as self-exclusion and short result sets.

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%, documenting both `slug` (with an example) and `limit` (1–5, default 3), so the baseline is 3. The description adds only the ordering guarantee and no additional parameter meaning, which is fair but not compensating beyond schema.

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 concrete resource (posts closest in meaning to a given post) and the mechanism (text-embedding similarity) plus the ordering (most similar first). That mechanism distinguishes it in spirit from search_posts/list_posts, but no sibling is named, so differentiation is left implicit.

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?

'Use to follow a thread of ideas from one post to the next' gives one concrete scenario, which is better than nothing. However it never states when to prefer search_posts or list_posts instead, nor does it note that a seed slug is required, so the agent must infer the boundary.

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