Remember a fact

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

Annotations already declare the write/non-destructive/non-idempotent profile, so the description's job is to add semantics — and it does, disclosing persistence scope (all future sessions, every AI tool) and a de-duplication rule against re-saving confirmed facts. It does not explain what preserve_as_blob does behaviorally or how confidence affects storage, leaving small gaps.

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 behavior is front-loaded in sentence one, but the trigger-phrase list ('capture', 'noted', 'remember this', 'log', 'store', 'don't forget') and long enumeration of fact types bloat the middle without adding much decision value; the DO-NOT exclusions are more useful than the synonyms.

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 write tool with no output schema, the description covers the two decision-critical things — when to fire and how to categorize — and annotations carry the safety profile. Audit-trail parameters and the blob extraction mode are left entirely to the schema, which is acceptable at 86% coverage.

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 86%, so the baseline is 3; the description earns an extra point by prescribing category semantics for troubleshooting ('Issue: <symptom>. Solution: <fix>'), which is real guidance beyond the enum listing. It says nothing about pr_number, commit_sha, preserve_as_blob, or source_session_id, but those are largely covered by schema descriptions.

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+resource ('Saves a new persistent fact about the user') plus the key scope property ('available in all future sessions across every AI tool'), which distinguishes it from session-scoped siblings like save_session and save_conversation_turn.

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?

Extremely explicit about when to trigger (user corrections, revealed preferences, first-time mentions of a person/tool/project) and when not to (transient values, facts already stored this session), with concrete trigger phrases enumerated. Alternative-routing is implicit but the inclusion/exclusion boundary is unusually sharp.

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