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

With no annotations supplied, the description carries the burden and does so well: it discloses deduplication by meaning, recency weighting, per-user/agent namespacing, a 20 000 item capacity, per-item billing at €0.001, and that auth comes from the Authorization: Bearer key. The destructive scope of 'all' (delete the whole space) is surfaced. What is missing is whether deletes are reversible and how failures surface, so not a full 5.

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?

Structure is strong and front-loaded: purpose first, then operational traits (dedup, cost, namespacing), then a compact parameter glossary. The parameter run-on is dense but each clause carries new information; nothing is filler.

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 10-parameter, multi-op tool with zero schema annotation coverage, the description covers purpose, auth, cost, limits, and all parameters, while an output schema handles return values. The remaining gap is op-selection guidance (search vs list vs spaces in practice), which keeps it from a 5.

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 it does completely: every one of the 10 parameters is explained with semantics and defaults (op values, space example 'user:42' with default 'default', text vs items batch shape, meta, query, top_k range 1–50 default 5, recency 0–1 default 0, comma-separated ids, all). It also clarifies value encodings (JSON array/object, bool) that the flat string schema leaves implicit.

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?

The description opens with a specific framing ('Long-term memory behind your key') and enumerates the concrete capabilities: add facts deduplicated by meaning, recall by meaning with an optional recency boost, list, forget. An agent can map each verb to an op value. It stops short of naming a sibling or explicitly differentiating from semantic_search/embed, but no sibling covers persistent namespaced memory.

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?

It states the default op (search) and the per-op parameter mapping, which implies when each op applies. However, there is no explicit when-to-use guidance such as 'use add before search' or 'use list to enumerate instead of search', and no exclusions or prerequisites beyond the cost note.

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