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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context with the row grain and the closed set of outcome states, which tells the agent what a returned row means. It says nothing about volume, default period behavior, or pagination cost, which matters for a log-style endpoint.

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?

A single sentence with the resource and the row grain front-loaded, followed by the most decision-relevant detail (the status values). No filler. It is terse to the point of under-specification rather than verbose, but the structure itself is sound.

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 9-parameter, filter-heavy log tool with no output schema and only 44% schema coverage, the description leaves too much unexplained — no mention of how feed_id or auction_id scope the log, no relation to list_ssp_feeds/list_ssp_auctions, and no note on default reporting period or result volume. The status enumeration is the only substantive compensation.

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 44% across 9 parameters, so the description should compensate — and it partially does: the enumerated statuses (win / lose / below_min_price / no_bid / timeout / error) effectively document the otherwise bare `status` string parameter, which has no schema description or enum. The remaining parameters (country, feed_id, auction_id, offset) get no clarification, and the relationship between `period` and date_from/date_to is left to the schema.

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?

Names the resource precisely (SSP auction bid log) and pins the row grain — one row per feed response — then enumerates the possible status values. An agent knows this returns bid-level records, not aggregates. It does not explicitly distinguish itself from list_ssp_auctions or list_ssp_feeds, which is the remaining gap.

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?

There is no statement of when to reach for this tool versus the two adjacent SSP list tools (list_ssp_auctions, list_ssp_feeds), and no guidance on typical filter combinations. Usage is only inferable from the name and the status enumeration.

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