get_memory

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context beyond them: the '…' truncation marker semantics and the hard failure mode when no entry matches the exact key.

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?

Three short sentences, zero filler, with the core action and the routing condition front-loaded before the error caveat.

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 single-item read tool with no output schema, the description covers what is returned (full untruncated text), when to reach for it, and what happens on failure. Nothing an agent needs to invoke it correctly is missing.

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 the baseline is 3. The description adds value on the key parameter by specifying exact-match semantics and tying the value back to recall's output, which goes beyond the schema's 'Exact memory key, as returned by recall.' Scope, project_id and include_archived disambiguation are left to 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?

States a specific verb and resource (full text of ONE memory) plus the exact selector (key from recall). It is immediately distinguishable from recall, recall_with_graph, remember and forget in the sibling list.

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?

Gives an explicit trigger condition: use after recall when content ends with the '…' cut marker. It also names the sibling source of the key and the failure prerequisite (errors on non-exact key). No explicit when-not-to-use case, but the context is clear.

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