knowledge_admin

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

Annotations declare destructiveHint=true and idempotentHint=false, raising the bar for behavioral disclosure, but the description adds nothing about what gets destroyed or modified, whether safety nets like backup, dry_run, or setup_mode=preview exist, or what side effects rebuild/repair/migrate have. The words 'rebuild,' 'repair,' and 'migration' are consistent with the annotations, so there is no contradiction—but the description fails to elaborate on any destructive consequence beyond the action names themselves.

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 12-word line is brief, but this is under-specification masquerading as conciseness. There is no lead sentence stating purpose, no grouping of related behaviors, and no hierarchy—just a flat list that duplicates the action enum. Brevity without information structure earns no credit.

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?

This is a high-complexity tool—15 parameters, 7 actions, conditional parameter-action interactions (force/dry_run for lint, clients/setup_mode for client_setup, migration_action/target_version for migrate), and destructive semantics—yet the description delivers zero operational guidance. Even with an output schema present, an agent cannot determine which parameters are valid for which action, what the safety modes do, or what output to expect. The definition is severely inadequate for its complexity.

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 only 20% (3 of 15 parameters documented: action, force, dry_run, each with a terse one-liner), so the description carries a heavy burden it does not meet. It adds zero meaning about parameters like backup, clients, setup_mode, integrity_mode, migration_action, target_version, include_missing, include_orphans, or include_broken_links, and it does not explain which parameters apply to which action. The description merely restates the action enum, which the schema already provides.

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, "Initialize/inspect/rebuild, client setup, lint/repair, drift, and migration," is a comma-separated list that maps almost one-to-one onto the action enum (init, status/checkpoint, client_setup, lint, drift, migrate). It never states a clear verb+resource purpose such as 'administers the knowledge base' or 'performs maintenance operations,' so an agent cannot tell what the tool fundamentally does or how it differs from siblings like knowledge_ingest or knowledge_document. This is close to restating the schema's own enum values in prose.

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?

There is no guidance on when to use this tool versus its seven siblings, no example workflows, no conditions, and no exclusions. The only usage signal is the action list itself, which the input schema already exposes. An agent gets zero help deciding between knowledge_admin, knowledge_ingest, and knowledge_page.

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