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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive); the description adds real behavioral context on top: recall is approximate ('a ranked sample can omit matches'), a return field is named and explained ('source_truncated marks partial text'), and the 4096 UTF-8 byte cap is clarified as not a token/session budget. That is exactly the kind of caveat an agent cannot get from structured fields.

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 purpose, then the three caveats in descending importance, with no filler sentences. The semicolon-chained fragment style is dense but slightly disjointed to parse.

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 six-parameter read tool with zero schema coverage and no output schema, the description covers recall limits and truncation well but leaves the entire input surface opaque. An agent still cannot tell what a 'scope' is, what workspace does, or what a preview object contains beyond the truncation flag.

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?

All six parameters have 0% schema description coverage, so the description carries the full burden, and it explains none of them. Scope, workspace, exclude_stale, current_source_hash, and limit semantics are entirely undefined, and the description never even names them; 'id and revision' refers to the sibling read_memory, not this tool's inputs.

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 first sentence gives a specific verb and resource ('Search authorized memory') plus the key qualifier 'bounded previews', which tells an agent this returns compact excerpts rather than full records. It also names the escalation sibling (read_memory), though it never distinguishes itself from the sibling tool literally named 'search'.

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 gives an explicit routing rule: use read_memory with id and revision when you need more than the preview. It also sets expectations that a ranked sample can omit matches, which tells the agent when results are not exhaustive. Missing is any statement of when to prefer this over the sibling 'search' tool.

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