kin_graph_status

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description goes beyond them by disclosing the semantics of the `sampling=last_settled_selected_graph` value and that a reading can be aged and reported as `stale` — genuine behavioral context about freshness that the annotations cannot express.

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?

Three compact sentences: what it returns, when to call it, and how to read the sampling value. Front-loaded with the payload, no filler. The final sentence is jargon-dense and could be parsed only by a reader already familiar with the vocabulary, costing it a point.

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 no output schema, the description carries the burden of describing return content, and it does name the count categories and the sampling/stale semantics. It does not explain how to act on an 'unindexed' backlog or what thresholds matter, leaving a modest gap for a diagnostic tool.

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 no parameter surface to document; baseline 4 applies. The description instead spends its words on interpreting the returned sampling field, which is the only semantically load-bearing token in the call.

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 the resource (the resolved graph) and the concrete payload: entity and relation counts plus embedded/pending/unindexed breakdown. That distinguishes it from search- and mutation-oriented siblings, though the opening phrase 'The graph this call is answered from' is slightly indirect about the fact that this is a status/diagnostic read.

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 an explicit trigger: 'Call it when a search returns less than you expect.' That is a clear context for reaching for this tool rather than semantic_search or the trace tools. It stops short of naming an alternative diagnostic to compare against, so it is a 4 rather than a 5.

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