quipu_merge_decisions

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

Annotations already declare readOnlyHint and non-destructive, and the description reinforces this with 'Writes nothing' and 'never sets a decision' - useful because the word 'merge' invites fear of mutation. It also discloses the read is bound to what was reviewed and that presentation output is the standard, unmodified view.

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?

Front-loaded with the operation and its two modes, and no sentence is filler. But the phrasing is compressed to the point of strain - 'The conflicts of merging... bound to what was reviewed' is a fragment, and 'bound to what was reviewed' is vague about what binding means.

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 six-parameter, nested-object read tool with no output schema, the description covers the two input modes, both boolean modifiers, and the return shape when present is true. It leaves slot_scoped's v1/v2 semantics to the schema, which documents them adequately.

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 coverage is already 100%, but the description still adds meaning: propose populates evidence but never a decision, and present returns the specific {decisions, presentation, view} shape with the markdown unchanged. It also clarifies that base pairs with incoming as 'its parent share', which the schema only half states.

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 names the exact resource - conflict rows for a share merge (incoming + base) or a fork promotion into ROOT - and specifies the row shape (base/ours/theirs plus provenance). 'READ.' plus 'Writes nothing' separates it from the mutating siblings quipu_merge_apply and quipu_merge_resolve, though it never names them explicitly.

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?

Usage is implied rather than stated: 'it never sets a decision' and 'Writes nothing' signal this is the inspection step before resolving, and the two input modes are spelled out. However, there is no explicit instruction about when to pick a fork versus incoming+base, or when to move on to quipu_merge_resolve.

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