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

Annotations already cover readOnly, idempotent, closed-world and non-destructive, yet the description adds substantial context beyond them: no inference of facts/deadlines/state, one-or-two-at-a-time elicitation, per-item labeling, and active redaction of ID, account and health details from the outreach summary. 'Stores nothing and sends nothing' directly explains why readOnlyHint is true even though the schema has create/update/discard actions.

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 trigger and the 'what it produces' list are front-loaded and dense with useful content, and the negative guidance is compact. The closing two sentences about being a listing service and no lawyer paying for placement/ranking are boilerplate unrelated to preparing a brief, and the central content sentence is a very long run-on enumeration.

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 13-parameter, nested-object tool with no output schema, the description covers purpose, content, elicitation behavior and privacy handling well. The remaining gap is the return payload: it never says what an invocation answers with (brief_id, preview text, suggested questions), leaving the agent to infer that from the brief_id parameter description.

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 77%, so the baseline is 3, but the description adds real meaning by mapping the brief's sections onto parameters (original words kept unchanged, confirmed state and city, dated chronology, people by role, evidence checklist, questions, deadlines as reported) and by describing the interaction pattern that populates them. One inconsistency: the description lists 'suggestion' as an item label, but facts.label only allows user_says, user_has and unknown.

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 and artifact ('Organizes ONLY what the person says into an editable brief') and then enumerates exactly what the brief contains, so an agent knows the output shape without opening the schema. It also explicitly distinguishes itself from the sibling preview_client_message and from answering legal questions.

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?

Opens with a concrete trigger ('Use when the person wants to get ready to talk to a lawyer about their own matter') backed by two example utterances, and gives explicit exclusions ('Do NOT use for general legal questions, homework, news or when the person only wants information about the law'). It also routes the downstream action ('to contact a lawyer the person picks, use preview_client_message') and the discard action, leaving little to infer.

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