lcm_expand

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

With no annotations, the description carries the full burden, and it only discloses the return-shape branching for summary expansion. It says nothing about the raw message expansion path implied by session_id/message_seq, the 2000-character cap, offset paging, or whether the operation is read-only. That leaves a mutation-free but behaviorally nontrivial tool under-described.

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?

One sentence, front-loaded with the action, using a parallel two-clause structure that maps cleanly onto the two branch outcomes. No filler and nothing buried.

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?

The main summary-expansion semantics are complete enough to call correctly, and the schema documents the raw-expansion parameters at full coverage. Still, the description never acknowledges that two distinct invocation modes exist or that results are paged, which an agent needs to interpret a truncated response.

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 each parameter is already documented in the schema; the description adds only the conceptual link between summary_id and which result set comes back. It contributes no format, constraint, or mutual-exclusivity guidance beyond that baseline.

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?

A specific verb ('drill into') applied to a specific resource ('a summary'), with the two outcome branches spelled out (leaf → source messages, condensed → parent summaries). It is distinguishable from lookup-style siblings like lcm_describe or lcm_grep, though it never names them.

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 only implied: the reader infers this is the tool to use once they hold a summary id and need to go one level deeper. There is no explicit when-to-use versus lcm_describe/lcm_recall/lcm_grep, and no statement of preconditions.

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