quipu_report

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, and the description reinforces the read-only nature. It adds genuinely non-obvious behavioral context: results reflect current structure only, rarity drives bridge ordering ('rarer bridges rank first'), and — importantly — Louvain communities are emergent clustering for surfacing, NOT an access boundary, which prevents an agent from misreading the output as a scoping/permission signal.

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 in the first clause, followed by the three deliverables and a closing caveat. Every sentence carries information — the ranking rule, the rarity ordering, and the community-semantics disambiguation all change how an agent reads the result. No filler or restatement of the name.

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?

With five optional params, no required params, and no output schema, the description carries the burden of describing the return value, and it does so by enumerating the three report sections and their ordering rules. Minor gaps remain: the shape/serialization of the returned report and the effect of the type/predicate filters are not covered.

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 coverage is 100%, so the baseline is 3; the description exceeds it by explaining what three of the five integers actually bound — hubs, surprising connections, and suggested questions correspond to the report sections it describes. It adds no guidance on how to choose values (defaults are only in the schema) and says nothing about the type/predicate projection restriction parameters, so it is not a full substitute.

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 opens with a concrete verb+resource ('Generate a live graph report') and then enumerates the exact three sections produced: top hubs ranked by PageRank with in-degree as a tiebreak, surprising inter-community bridges, and auto-suggested questions. This is far more specific than any sibling such as quipu_stats or quipu_spotlight, though it never names an alternative, so differentiation is by content rather than by explicit contrast.

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 states the report is read-only and derived from the current graph structure, and the community caveat implies analysis/exploration is the intended use. It does not say when to reach for this versus quipu_stats, quipu_spotlight, or quipu_query, nor does it give any exclusion or prerequisite (e.g. graph must be non-empty for meaningful hubs).

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