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

Annotations cover safety and idempotency (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds the critical behavior the annotations cannot express: provided fields overwrite, omitted/null fields are preserved, and empty string or empty list clears a field. That tri-state merge contract is exactly what an agent needs to avoid accidentally wiping data.

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 purpose followed by the merge contract and return statement. The long field enumeration is justified by the near-zero schema coverage, though it reads as a dense run-on rather than a scannable structure.

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 nested-object mutation tool, the description covers the write semantics, field inventory, and return behavior, with annotations carrying the safety profile and an output schema existing for the return value. Remaining gaps are the absence of sibling routing (vs add_career_fact / get_career_memory) and any note on permissions or limits.

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 effectively near zero (only remote_preference is annotated), so the description must carry the burden and only partially does: it lists every field name and the update semantics, but never explains what fields like blockers, search_stage, or seniority_goal actually mean. The schema itself documents the free-text example only for remote_preference, so the description adds the field inventory but not per-field meaning.

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 pair (remember/update) and the exact resource: the user's structured career preferences, enumerated field by field. An agent immediately knows this is the write path for profile-level preferences. It does not, however, name or distinguish itself from siblings like add_career_fact or get_career_memory.

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?

Usage is implied through the update semantics (overwrite/keep/clear) rather than stated. There is no explicit 'use this instead of add_career_fact when...' routing, and no mention of when to prefer this over the per-fact tools, so the agent must infer the boundary itself.

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