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

Annotations already declare readOnly/idempotent/non-destructive, so 'Read-only' is redundant, but the description adds genuinely new behavior: a named error taxonomy (api_key_required, subscription_required with checkout_url, brand_not_found, round_not_found) plus the note that round_not_found names the stored weeks available. That is real auth/failure context not present in the annotations.

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?

Every sentence carries information and the read purpose is front-loaded, but the opening sentence is an unusually long multi-clause run-on describing the entire return payload, which is harder to scan than the terse 'Pass brand_id. Read-only. Errors: ...' that follows.

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 two-parameter read tool with an output schema, annotations covering safety, and 100% schema coverage, the description supplies the missing pieces: prerequisite tracker, payload outline, error set, and default-week behavior. Nothing an agent needs before invoking it is absent.

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 100%, so the baseline is 3. The description still adds framing beyond the schema by tying the optional week parameter to the payload shape — omitting it returns the latest stored week 'in full' along with the change from the previous stored week — and by restating the brand_id requirement in flow order.

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?

Opens with a specific verb and resource ('read a tracker from create_tracker') and then enumerates exactly what comes back: brand, rivals, prompts with ids, every stored week with mention/citation share, plus one week in full. This is far more specific than the sibling names add_round/create_tracker and lets an agent tell read from write without opening a schema.

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?

It states the precondition (a tracker produced by create_tracker, whose brand_id must be passed) and implies the read counterpart to add_round. It does not explicitly state when to prefer this over sibling read-ish tools such as score_answer_share or get_feedback_reply, so it stops short of full routing guidance.

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