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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds substantial behavioral context: the ranking criteria ('degree, then observation count, then name'), the response shape with kept/dropped counts, that it never raises protocol errors but returns an error object, and that retries are safe after input correction. This is rich, non-redundant transparency.

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 dense but remarkably efficient: a one-sentence purpose, a concrete example, usage boundaries, and error behavior. Every sentence adds information; there is no filler or repetition of the schema, and the most important points are 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?

Given the rich annotations, full schema coverage, and output schema, the description still manages to fill all important gaps: return format, ranking algorithm, error semantics, idempotence reassurance, and a realistic usage example. There is no missing context an agent would need for correct invocation.

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 input schema already documents all three parameters (graph, max_entities, keep) with descriptions, defaults, and constraints, so the baseline is high. The description adds meaningful usage semantics by showing a typical input/output example and explaining what 'keep' means behaviorally ('keeps anything you name outright') and how ranking works, which goes beyond the schema's mechanical definitions.

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 clearly defines the tool as 'Shrink a memory to the part that still earns its place' and details exactly what happens: ranking entities, keeping named ones, and dropping the rest with their relations. It explicitly distinguishes this from sibling tools like graph_lint, which is for finding wrong facts.

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?

The description gives explicit when-to-use guidance ('Use when a graph has outgrown the context you can spend on it') and when-not-to-use guidance ('Not for removing wrong facts - graph_lint finds those'). It also names the alternative tool, making the usage boundary crisp.

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