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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds almost no behavior beyond that: it doesn't say how similarity is computed, whether results are ranked, whether the source chunk is excluded, or how many results come back by default.

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?

A single sentence with zero filler, and the core purpose is front-loaded before the id-provenance hint.

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 simple read-only two-parameter tool with full schema coverage and no output schema, the description is minimally sufficient to call it. It leaves the agent guessing about result ordering and what the returned chunks look like, which matters for a 'similarity' tool.

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 both parameters are already documented including the 1-50 range and default of 10. The description only restates that message_id comes from rag_search, which is marginally useful provenance but adds no syntax or format detail.

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?

Specific verb ('Find') plus resource ('document chunks similar to a source id') with the input's provenance spelled out. It implies a follow-up to rag_search but doesn't explicitly contrast itself with that sibling or with memory_search, so differentiation is only implicit.

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 parenthetical '(the message_id returned by rag_search)' hints at the correct two-step workflow, so usage is inferable. But there is no explicit statement of when to use this instead of rag_search or memory_search, and no exclusions or prerequisites beyond the id source.

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