personal_neighbors

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

With no annotations, the description carries the full burden and does so well: it discloses the default empty documents payload, the doc_count/doc_char_count signal, the summary_max_chars=0 opt-out, and the reversible but dangerous include_documents=True mode. It even warns about payload explosion from previous behavior.

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?

Each sentence in the description adds a distinct fact: purpose, phase, default payload, expansion guidance, trim control, and the hard include_documents rule. It is dense but not padded, and the most important purpose line is front-loaded.

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 tool with no annotations and no schema param descriptions, the description covers the main call pattern, safety limits, and expansion workflow; the output schema can carry return structure. It is still not fully complete because only_len and id semantics are left to inference, but an agent has enough to call it safely in most cases.

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?

The schema has 0% description coverage, so parameter explanation must come from the description. It explains include_documents, summary_max_chars, and depth constraints, but leaves only_len and the required id parameter implicit, which is a clear gap.

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 opening line defines a cheap neighborhood map with nodes, edges, trimmed summary, and budget, and later positions it as Phase A of a two-phase read. This is specific, but the description never states a verb and does not explicitly differentiate it from sibling personal_graph, so it stays below the top score.

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 frames the tool as Phase A of a two-phase read and points to personal_get_node as Phase B for expansion. It also gives a hard exclusion rule: never use include_documents=True with depth>=2 because it saturates the graph. This meets the explicit when/when-not/alternative bar.

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