memory_retrieve

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavior beyond that: results are lossless, metadata is included, storage is isolated per project_path, and the runtime surfaces the actual embedding/storage backend — useful for trusting the result's provenance.

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-loaded with the core action and lookup mode, then alternatives and constraints, with no filler. The trailing clause about runtime-reported embedding/backend is slightly cryptic but still earns its place as provenance information.

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, the description does state the return is lossless and carries metadata, plus the isolation guarantee. It stops short of saying what happens when the key is absent (empty result vs. error), which is the one behavior an agent would still have to guess.

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 schema already documents all three parameters, including project_path isolation. The description's only addition is that matching is exact rather than fuzzy, which is meaningful but thin; the project-isolation note largely restates 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 ('Read back a value previously stored via memory_store') and pins the lookup mode as exact (namespace, key), which cleanly separates it from the semantic-oriented memory_search sibling. An agent can pick between the two without opening either schema.

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 clear context ('Use for project-scoped persistent memory') and one explicit exclusion ('Never import personal memory automatically'). It does not explicitly name memory_search/memory_list as the alternative when exact match is not known, leaving that routing to inference from the word 'exact'.

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