list_memories

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: newest-first ordering and a hard cap of 100 results. It does not mention pagination/offset behavior or what happens past the cap.

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 core purpose and ordering lead the description, with parameter detail following in a compact Args block. Slightly boilerplate in format, but no filler sentences and everything stated earns its place.

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?

With an output schema present, return values need not be described, and annotations cover safety. Purpose, ordering, filter, and cap are all present, leaving only the sibling-disambiguation gap ('recall' vs 'list_memories') as a meaningful omission for a 2-parameter read 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 0%, so the description must compensate and largely does: 'limit' is explained with its ceiling ('at most 100', a constraint absent from the schema) and 'session' is explained as an optional conversation-id filter. It omits the default values (20 / null) that the schema carries.

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?

States a specific verb and resource: list stored messages, with ordering ('newest first'). That is clear and actionable, but it never distinguishes itself from the sibling 'recall', which an agent would reasonably consider a competing option for retrieving memories.

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: 'most recently stored' plus the 'session' filter signal that this is for browsing recent items or scoping to one conversation. No when-to-use statement, no mention of when to prefer 'recall' or 'fit_context' instead, and no prerequisites.

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