Derived Knowledge

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description reinforces this with the key operational fact that index_build/graph_build overwrite the prior in-memory projection. It adds genuinely non-derivable context: builds are audited, the Novel file remains authoritative, and read-only actions never mutate Novel state. It stops short of describing lifetime/eviction of the in-memory projection or any permission requirements, so it is strong but not exhaustive.

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, then the when/when-not blocks, with no filler sentences; every clause maps to an action or an alternative. It is dense and readable, though the run-on action list would scan faster as a bulleted or structured breakdown.

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 an output schema present, return values need not be explained, and annotations already carry the safety profile. For an 11-action multiplexed tool the description supplies purpose, per-action intent, mutation semantics, authoritative-source rules and sibling alternatives — nothing an agent needs in order to pick the right action is missing.

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, but the description goes beyond the schema's terse 'index_* actions operate the semantic index' by explaining what each action actually does, which is the primary discriminator among the five parameters. It does not add format or constraint detail for limit, query, item_id or node_id beyond the schema, so it earns 4 rather than 5.

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 ('Manage derived, in-memory knowledge over Novel sources') and immediately decomposes it into two concrete subsystems: a semantic index for advisory text ranking and a typed knowledge graph. The per-action enumeration and named sibling redirects make it distinguishable from manage_lore, manage_corpus and manage_ruleset without opening any schema.

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?

Contains an explicit 'Use when:' clause mapping each of the 11 actions to its task (build, staleness check, list, rank, read relations/graph/nodes/edges/neighbors) plus a 'Do NOT use when:' clause with three named alternatives and the exact alternate action (manage_ruleset action: search). This is the rare definition that routes rather than merely describes.

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