Session Memory

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

With annotations already declaring destructiveHint=true and readOnlyHint=false, the description adds meaningful context: deletion clears only derived text (scoping the destruction), edits require the current revision (concurrency), history survives session expiry under SQLite persistence, and no provider/inference/upload/global search occurs. It also discloses the isolation caveat that caller-selected scope is not authenticated identity, which is a genuine security nuance beyond the annotations.

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?

The core purpose is front-loaded in the first sentence and each subsequent sentence carries a distinct behavioral fact. The telegraphic style ('No provider, inference, upload or global-memory search occurs') is terse but not padded.

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?

An output schema exists, so return values need not be explained, and the nested request object is fully documented in the schema. The description covers persistence, concurrency, isolation and non-occurrence traits, though it leaves the list/search/compact actions of the enum undescribed, a minor gap for a 7-action tool.

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 baseline is 3, but the description adds real meaning: 'edits require the current revision' maps to expected_revision semantics, and 'scope is isolation, not an authenticated multi-user identity' clarifies the scope parameter's intent beyond the schema's exact-match note.

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 names concrete verbs (inspect/read/edit/delete) and resources (original history, explicitly scoped derived profile), which lets an agent distinguish this from the many knowledge_*/media_* siblings. However, the terminology is opaque ('derived profile') and it only accounts for the get/set/delete/history actions while the schema's action enum also exposes list/search/compact, leaving part of the purpose unstated.

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?

The description gives behavioral conditions ('edits require the current revision', 'deletion clears only derived text') but never states when to choose this tool over an alternative or when not to use it. No sibling is named and no selection condition is offered, so the agent must infer usage entirely.

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