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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new behavior: errors never surface as protocol errors and instead return {"error": "<what is wrong and how to fix it>"}, plus an explicit retry guarantee after input correction. The worked example output discloses the concrete response shape far beyond what the annotations convey.

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?

Front-loaded with the core purpose, then defect types, then a concrete example, then usage rules and exclusions. The large return-value example is somewhat redundant given an output schema exists, and the 'FREE.' fragment is stray, but no sentence is wasted overall.

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?

Covers purpose, defect taxonomy, example output, when-to-use, sibling exclusions, and error/retry semantics for a single-parameter read-only tool. An agent has everything needed to select and invoke it correctly without opening the schema.

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?

Only one parameter and schema coverage is 100%, so the schema already documents 'graph', and the description's {"graph": {...}} example adds little beyond that. The graph document is a nested open object, and neither schema nor description explains its internal structure, but with full coverage the baseline 3 is appropriate.

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?

States a specific verb+resource (lint a memory graph) and enumerates the exact defect classes it finds: dangling relations, orphan entities, near-duplicate names, contradictions. It is immediately distinguishable from graph_diff and graph_compact, which it names explicitly.

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?

Gives both positive triggers ('before trusting a graph you did not build, or on a schedule as memory grows') and explicit exclusions with the sibling that handles each ('Not for comparing two graphs (graph_diff) and not for shrinking one (graph_compact)'). Nothing is left to inference.

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