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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real value: append-only behavior, the 15-fact read window used by vacancy analysis, the return value (fact_id), and the 'invalid_payload' error condition with its 500-char limit. It doesn't cover auth requirements or explicit rate limits, but the behavioral disclosure is strong.

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 purpose, then scope, then error semantics in a compact few sentences. The long enumeration of sibling field names is slightly dense but earns its place by clarifying the boundary with upsert_career_memory.

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 the description needn't restate return structure, yet it still names the returned fact_id and the error case. Combined with the append-only semantics and the downstream read window, the description is complete for an agent to call this correctly.

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 0% for the single nested fact parameter, so the description must compensate and largely does, explaining the 1..500 character constraint and giving example facts. It doesn't fully specify the nested 'input' object shape, but the single meaningful field is well covered.

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 ('Remember a single durable career fact about the user') and immediately grounds it with concrete examples. The append-only scope and contrast with the sibling upsert_career_memory makes the boundary clear.

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?

Explains the append-only semantics and that vacancy analysis reads the 15 newest facts, and it points to upsert_career_memory for structured-field equivalents. It does not spell out when to prefer this over upsert_career_memory beyond the structured-vs-durable distinction.

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