setMessages

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

This is exceptionally transparent: it discloses upsert-by-number semantics, that only passed messages are touched, that class description is read and carried over, the 73-character cap with cut reporting, self-managed locking, no activation requirement, and immediate persistence to T100. All of this goes well beyond the minimal readOnlyHint/destructiveHint annotations.

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 dense but every sentence earns its place: each covers a distinct behavioral or environmental constraint. It is front-loaded with the core purpose, and the supporting detail is organized logically from update semantics to cap, lock, visibility, and transport.

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 write tool with four parameters and no output schema, the description covers what an agent needs: exact update semantics, edge cases, hard limits, prerequisites, side effects, and even what the response mentions ('says what was cut'). There is no significant missing operational context.

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?

Although the schema already has 100% coverage, the description adds meaning the schema cannot: the upsert behavior, 'field left out keeps its value', the 73-character truncation, the transport requirement outside $TMP, and the default behavior of selfExplanatory. This substantially helps an agent set correct parameter values.

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 opens with a specific verb-resource pair: 'Add or change messages of an existing message class.' It clearly distinguishes the tool from siblings like getMessages or createMessageClass by scoping it to existing classes and partial message updates, and even clarifies that deletion is not possible.

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 strong contextual guidance: it explains partial updates, that omitted fields are preserved, that a transport request is required outside $TMP, and that messages appear in T100 immediately. It does not explicitly name alternative tools or say 'use X instead', so it stops short of the highest benchmark.

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