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

Goes well beyond any annotations by disclosing 404 semantics for foreign memory_id, pagination shape {count,next,previous,results}, newest-first ordering, wildcard '*' matching, and crucially the memory_key secrecy model ('a different key sees nothing', lose it and data is unreachable). Also surfaces pricing and free-tier limits.

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?

Front-loads the dual-mode behavior in the first sentence, then covers filters, key, and pricing. Dense but every clause carries operational meaning; slightly busy with pricing and secret-key caveats that could be compressed.

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 no output schema and no annotations, the description carries the full burden and does so: it documents return shape, error behavior, ordering, auth model, and payment. An agent has everything needed to call this correctly.

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 all nine parameters are already documented in the schema. The description adds the 'at least one filter' constraint and '*' wildcard behavior, which is useful but largely compensates for coverage that's already present.

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 (read/returns memories) and resource, and clearly distinguishes two modes (single memory by id vs paginated list). It also contrasts with siblings like search_memories by noting exact-id vs filter listing.

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?

Explains when memory_id alone fetches one item vs when a filter (user_id/agent_id/app_id/run_id) is needed, and at least one filter is required for listing. It doesn't explicitly say when to prefer this over search_memories, but the filtering and pagination context is clear.

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