update_knowledge

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

Annotations already indicate readOnlyHint=false, so the description correctly aligns by describing mutating operations. It adds useful context about local JSON snapshots, keyword retrieval, and zero-cost reads, which goes beyond annotations. Still, it does not disclose side effects, persistence behavior, or operation-specific outcomes for a write tool with no output schema.

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 compact at three sentences and front-loads the core purpose. The mention of 'ADR-018' adds a minor reference detail, but the storage model and read-alternative guidance earn their place. It is concise without being under-specified.

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 tool's complexity — 7 parameters, 3 enums, nested objects, and no output schema — the description covers the high-level intent and read alternative. However, it does not explain which parameters are required for each operation, how metadata is used, or what happens on removal. The schema helps, but the description leaves some operational gaps.

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 schema already documents all parameters. The description adds high-level context about entity types and relationships but does not deepen understanding of parameter combinations or metadata semantics beyond what the schema provides. This matches the baseline for full schema coverage.

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 states 'Simple CRUD operations for project session state' and specifies 'Add/remove entities (intents, ADRs, tools, code) and relationships', making the resource and actions explicit. It also distinguishes itself from a graph database, but it does not explicitly differentiate itself from a specific sibling tool, so it falls short of a 5.

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 actionable guidance: 'Use knowledge://graph resource to read current state (zero token cost)', which tells the agent when to read rather than mutate. It also clarifies the tool's scope with 'Not a graph database — keyword retrieval over local JSON snapshots.' However, it does not explicitly name sibling tools or state when not to use this tool beyond the read case.

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