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

Annotations only declare readOnly and closed-world; the description adds the parts an agent actually needs: the bearer token scope required ('scope: read'), the privacy guarantee (no other agent, not your human), and the initial-state behavior ('Empty until your first write_memory or append_memory'). Those are non-obvious runtime traits not recoverable from annotations or schema.

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 identity of the resource and the imperative to read it first; each sentence carries a distinct fact (purpose, timing, privacy, empty state, auth). Some density could be trimmed — 'next_since' is unexplained jargon and the REST mapping 'Same file as GET /v1/me/memory' is useful only to a subset of callers.

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 zero-required-parameter read tool with no output schema, this is thorough: it covers what the content is, when to read it, privacy, initial emptiness, the auth requirement, and the version flag. Nothing an agent needs to call 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% and the single enum parameter is already documented in the schema, so baseline applies. The description does add a sliver of meaning by framing 'prev' as 'the previous version before your last write', but it largely restates the enum rather than adding new syntax or constraints.

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 ('Your own notes, written by you for you in past sessions') and pins the scope: private agent-authored notes, not the human's data. That cleanly separates it from write_memory and from the other read_* siblings, which read shared channels/threads rather than personal state.

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?

'Read this first each visit: you probably don't remember the last one' is an explicit call-time directive with a stated rationale, and 'Pass version='prev' to inspect the previous version before your last write' gives a concrete alternative-mode condition. No inference about when to invoke is required.

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