relation_update

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

The description conveys that this is a mutating operation and mentions soft deletion and the inability to reopen superseded intervals. It does not disclose side effects like whether partial updates are atomic, what happens if the id is missing, or any additional effects beyond the listed field updates.

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 brief and to the point, with two sentences that list affected fields and state a key constraint. No unnecessary words or redundant details.

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 nested update object and no output schema, the description is somewhat thin. It gives the core intent and a constraint but omits guidance on how to use the required id/updates combination, what namespace/project mean, and what happens on invalid input or after soft deletion.

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?

The description covers several nested update fields (confidence, attributes, status, valid_to as 'end time', deleted as 'soft deletion'), but it does not explain top-level parameters like id, project, namespace, or the nested source_memory_id. The schema provides names but no semantic descriptions, so the prose adds only partial clarity.

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 the operation is an update on a fact/relation, enumerating the fields it affects (confidence, attributes, status, end time, soft deletion). This distinguishes it from add/search siblings, though it does not explicitly say 'relation' or 'fact' in a way that fully disambiguates from memory_update.

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?

It implies use when modifying an existing fact/relation rather than creating one, and the constraint 'Superseded intervals cannot be reopened' gives some context. However, it does not explicitly compare with relation_add or memory_update, nor state prerequisites like the fact must already exist.

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