Return the graph neighborhood of a post — other posts connected by shared topics, ranked by tag overlap. Use this to traverse the site as a network ("what connects to this?") rather than re-running keyword searches. Same-series parts are excluded (use get_series for those).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The post ID or slug to find neighbors for | |
| limit | No | Max related posts (default 5, max 15) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses the ranking by tag overlap and the exclusion of same-series parts. It adds meaningful behavioral context without contradicting the annotation, making the tool's behavior more transparent.
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?
The description is three concise sentences that are front-loaded: first defines the purpose, second gives usage context, third states an exclusion and alternative. Every sentence earns its place with no 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?
Given the tool's low complexity and the rich annotations/schema, the description covers the core behavior, use case, and key constraint. With no output schema, it sufficiently conveys what the tool returns, making it complete.
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?
Both parameters are fully described in the schema (id and limit with default/max), so the description adds little beyond the schema. The mention of tag overlap gives context for id but doesn't provide additional parameter-level detail, hence the baseline score of 3.
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?
The description uses a specific verb+resource ('Return the graph neighborhood of a post') and explains the result: other posts connected by shared topics ranked by tag overlap. It clearly distinguishes itself from siblings by mentioning get_series for same-series parts and contrasting with keyword searches.
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?
It explicitly states when to use the tool ('to traverse the site as a network') and when not to ('rather than re-running keyword searches'). It also directs users to get_series for the excluded same-series parts, providing a clear alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or action: single post retrieval, graph traversal, series navigation, site metadata, project listing, guestbook read/write, search, and quote verification. Even the related/series tools have explicit disambiguation in their descriptions.
All tool names follow a consistent verb_noun snake_case pattern: get, list, read, search, sign, verify. No mixed conventions or vague verbs.
With 9 tools, the set is well-scoped for a blog/knowledge-graph server. Each tool earns its place and there is no redundancy or bloat.
The surface covers the full read lifecycle (search, retrieve one, related, series), site context, projects, guestbook (read and write), and even a provenance-check tool. No obvious dead ends or missing core operations.