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

Goes well beyond the annotations: discloses a 6000-character budget, a 30-storage-changes-per-hour rate limit, the PII/secret prohibition, and the expectation to tell the user what was saved. Annotations only cover mutation/openWorld flags, so this extra context is genuinely additive rather than redundant.

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-loads the purpose and payoff, then compresses mode semantics, limits, content policy, and user-facing behavior into short clauses with zero filler. Every sentence carries an instruction the agent needs.

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 two-parameter write tool with no output schema, the description covers limits, rate limiting, mode semantics, acceptable content, and even the post-call user interaction. Nothing an agent needs to invoke 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%, so the baseline would be 3, but the description adds real meaning: 'append' adds a new point versus 'replace' rewriting and being the tool for condensing. It also clarifies the 6000-character total against the schema's 20000 maxLength, removing an ambiguity the schema alone would leave.

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 ('Save your personal instructions about this user on the server') plus the payoff ('so any agent they start later continues with the same context'), and enumerates what belongs in it (preferences, rates, red flags, proposal style). An agent can distinguish this from get_agent_context or save_setup without opening 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 clear operational guidance: append adds a point, replace rewrites the whole text and is the choice for condensing, plus content rules (keep short and current, no secrets or third-party personal data). It does not explicitly name the read-side sibling (get_agent_context) or state when not to save, which keeps it from a 5.

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