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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description adds real behavioral context beyond that: the record starts personal and unverified, immediately applies to the token owner's agents, and a moderator can later make it shared. Auth/rate-limit details are absent, but the lifecycle disclosure is genuinely useful.

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?

Two sentences, front-loaded with the core action before the visibility and `level` details. Dense but every clause (trigger, secret caveat, visibility lifecycle, level semantics) earns its place; only minor cost is that the level list is inline rather than scannable.

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 7-parameter creation tool without an output schema, the description covers the trigger, the safety caveat, the visibility lifecycle, and the one ambiguous required parameter's semantics, while the schema already documents the remaining fields. Nothing an agent needs to call this 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 description coverage is 86% (above the 80% baseline of 3), but the description goes further by spelling out the four `level` values with concrete scope examples (company/Git/cloud/CI, user/preferences, project/infrastructure, repository/conventions) — meaning the schema's bare enum does not carry. This is a real addition over structured data.

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: "Saves a confirmed fact, rule or recipe as an agent memory record." Combined with the trigger condition (user asks to keep knowledge), an agent can distinguish this create tool from the sibling memory_list/read/update/delete tools without inspecting any schema.

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 a clear when-to-use ("when the user asks to keep knowledge for future agent work") plus an explicit restriction ("secrets only at the user's direct request"). It does not name sibling alternatives such as memory_update for editing an existing record, so it stops short of full routing guidance.

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