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

The annotations already establish this is a non-read-only, non-destructive, non-idempotent mutation. The description adds the useful behavioral detail that submissions become memory proposals subject to review rather than committed memories. It does not say whether repeat submissions create duplicates or whether omitted optional fields degrade the proposal, which matters given idempotentHint=false.

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 with no filler, and the payload categories are front-loaded before the outcome clause. It is efficient, though the parenthetical list is slightly dense compared to a short structured breakdown.

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 mutation with full schema coverage and annotations, the description covers purpose and downstream effect but leaves behavioral gaps (duplication on repeat calls, whether the session must be tied to an existing repo record) that an agent cannot resolve from structured fields alone.

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 100%, so every parameter already carries its own description, including the repo format and the list_repos fallback hint. The parenthetical field list in the description merely restates those parameters without adding format, size, or quality guidance beyond the schema.

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 gives a concrete verb ("Submit") plus the exact payload categories (task, summary, files, commands, errors) and the downstream effect (Memmo proposes memories for review). It is clearly distinct from siblings like search_memory or get_repo_context, though it never names propose_memories explicitly as the related tool.

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?

"Submit what you just did" implies the timing (end of a work session) but gives no explicit when/when-not guidance, no prerequisites, and no reference to alternatives such as propose_memories. An agent can infer usage from context but nothing is stated outright.

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