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

Annotations already cover readOnlyHint, destructiveHint, and openWorldHint, so the safety profile is given. The description still adds real value beyond them: result ordering (newest first), workspace scoping, tokenised match semantics for query, and ANY-of (OR) semantics for tags.

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?

Four tight sentences, front-loaded with the core action and scope, then filters. Every sentence adds information an agent needs; nothing is restated padding.

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 simple read tool with annotations covering safety, the essentials are present. However, with no output schema, the agent gets no sense of what a returned "fact" looks like or how `limit` defaults, and there is no guidance on what an empty result means.

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 carries the full burden. It does well on query ("word-tokenised match") and tags (ANY-of, with examples), but the third parameter `limit` is never mentioned — no default, no mention that it caps results at 100 — leaving one of three parameters explained only by its bare 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?

A specific verb ("Recall") plus a precisely scoped resource ("the caller's remembered facts... from their active workspace") with ordering stated ("newest first"). "Read-only" implicitly separates it from the mutation siblings (forget_memories, update_memory, merge_memories) without ambiguity.

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 usage context: an unfiltered call returns everything newest-first, filters are optional, and combining query+tags "narrows further." It never states when NOT to use it or names the mutation siblings to redirect deletion requests, so it stops short of full when/when-not guidance.

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