knowledge

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it discloses nothing: no side effects, no destructiveness (cleanup, supersede, update), no mutation warnings, no auth/provenance requirements, no fallback behaviors. The description is a name list, not a behavior statement. The schema hints at some behaviors (e.g., 'fail honestly when unsupported', LLM fallback), but the description itself adds zero behavioral context.

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 single sentence is compact, but this is under-specification, not conciseness—a 12-action, 51-parameter monolith is summarized as one comma-separated verb list. There is no grouping of read vs. write vs. administrative actions, no hierarchy, and no explanation of the operations. The structure front-loads nothing usable; it reads like a table of contents rather than a tool definition.

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?

For a tool with 12 actions, 51 parameters, no output schema, and no annotations, this description is severely incomplete. It does not define the semantics of any action, explain which parameters apply to which actions at a conceptual level, describe return behavior, or list side effects. The schema's per-parameter notes partially compensate, but the tool-level knowledge needed to select and invoke actions correctly is essentially absent.

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 description coverage is 100%, so the baseline is 3 even without parameter info in the description. The schema already documents each parameter including action-scoping notes like '(for action=search)' and constraints such as 'values above 100 are capped'. The description adds no parameter-level meaning, but at this coverage level it does not need to.

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 identifies the resource ('knowledge graph') and lists 12 operation verbs (store, search, get, list, update, details, note, cleanup, synthesize, stats, supersede, audit), which is specific enough to avoid being a tautology. However, it is a flat catalog of operation names with zero explanation of what each operation means, and the 'Unified' framing does little to distinguish this monolith from siblings like store_finding, update_finding, or search_shared_memory. An agent still cannot tell what 'supersede', 'note', or 'cleanup' actually accomplish.

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?

No when-to-use or when-not-to-use guidance exists anywhere in the description. Given sibling tools named store_finding, update_finding, search_shared_memory, and consult, there is heavy potential overlap with the store/update/search actions of this tool, and the description provides zero routing criteria. An agent is forced to open both schemas and infer the boundary, which is exactly what the description should preempt.

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