remember_person

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

With no annotations provided, the description carries the full burden. It discloses the important guardrail behavior: refusing duplicates and conflicting overwrites, and requiring user confirmation before proceeding. This is significant behavioral insight. However, it doesn't disclose what gets destroyed on overwrite, whether the operation is idempotent, or any persistence details.

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?

Three sentences, no filler. The core purpose is stated in one line, then the guardrail behavior follows. It's front-loaded with the verb+resource. Could arguably merge or elaborate slightly, but overall it's economical and earns each sentence.

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?

Despite having an output schema and only 1 required param, the 13-parameter tool with 0% schema coverage needs more. The description explains the confirmation workflow well but says nothing about what the tool returns, how fact_key/fact_value interact with the person-record fields, or whether there are constraints on the data (format, length). For a 13-param mutation tool, this is marginally adequate but has clear gaps.

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 0%, so the description has the burden to explain parameters. It covers confirmed_new and overwrite semantics via the guardrail text, but the remaining 11 parameters (city, email, phone, country, summary, fact_key, full_name, fact_value, current_org, current_role, linkedin_url) are entirely undocumented. The description explains the two boolean toggles but nothing about the data fields themselves. With 0% coverage, the baseline 3 is appropriate but the description falls short of fully compensating.

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 states a clear verb+resource: "Create or update a person from conversation." This distinguishes it from siblings like get_person (read), search_people (search), and add_fact (adds facts to existing person). It's clear and specific, though it could more explicitly differentiate from add_fact which also relates to person data.

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 explicit guidance on the guarded workflow: "By default this refuses similar-name duplicates and conflicting overwrites. Ask the user, then retry with confirmed_new or overwrite only after they decide." This tells the agent when to use confirmed_new vs overwrite parameters, which is valuable behavioral guidance. However, it doesn't cover when to prefer add_fact or update via other tools.

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