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

Adds real behavioral detail beyond annotations: partial-update semantics ('only the passed fields change'), that null clears a field, the read mode returns empty-required-fields and previously-guessed details, that EEO values are optional/sensitive and used only for voluntary self-ID, and that nothing is sent to employers. The destructiveHint=true annotation is largely covered by the explicit 'null clears one' note, though it never states a field overwrite cannot be undone.

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 read/update contract and modes before the safety caveats and the sibling hand-off, so the call-critical information comes first. It is dense across ~10 sentences; the EEO enumeration and 'nothing is spent' sentence could be tightened, but no sentence is pure filler.

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 33-parameter mutation tool with an output schema, the description supplies what structured fields cannot: the read/write mode contract, partial-update and clear semantics, an explicit no-guessing rule, sensitivity handling for EEO fields, and routing to the correct preference tool. An agent has everything needed to invoke it safely.

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?

With 100% schema description coverage the baseline is 3, but the description adds meaningful semantics the schema lacks: null clears a field, only passed fields mutate, and EEO fields accept prefer_not_to_say to decline. It also enforces the source rule 'save only answers the user gave you, never guesses', which governs every parameter.

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 (read/update) and the exact resource (the application profile: contact details, work authorization, education, legal declarations, EEO answers). It immediately distinguishes itself from the look-alike sibling by naming getmattered_update_job_preferences as the wrong tool for matching preferences.

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 explicit mode selection: call with no fields to read profile plus open questions, pass fields to save. It names the exclusion (job preferences → getmattered_update_job_preferences) and the follow-on tools (getmattered_get_matches, getmattered_apply).

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