overview

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

With no annotations, the description carries the full burden, and it discloses useful behavioral traits: it is 'cheap' and 'shallow', returns tallies rather than raw records, and is read-only in nature (a 'map'/'returns'). It does not explicitly state absence of side effects or any access constraints, but the read-only character is strongly implied by the framing.

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?

Purpose is front-loaded, followed by the grep comparison and the session-start guidance. The first sentence is dense with a long parenthetical enumeration, but every clause carries information; no filler sentences.

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?

An output schema exists, so return values needn't be re-explained, and there are no parameters to cover. The description supplies the missing pieces an agent needs: what shape comes back, why it beats grep, and when to invoke it.

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 tool takes zero parameters, so there is nothing to document beyond the empty schema. Baseline for a parameterless tool is 4.

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 names a specific resource (the project's spine structure) and enumerates exactly what it returns: spine roots, part_of children as branches, per-subtree tallies, whole-graph totals, and top open questions. It is clearly distinguishable from siblings like open_questions or briefing because it returns the aggregated shape in one call.

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 gives explicit when-to-use ('at the start of a session, before anything else'), a named alternative it supersedes ('prefer this over grepping graph files'), and the reason the alternative is insufficient. The graph://project/overview resource is offered as an equivalent path, leaving nothing to inference.

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