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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully carried by structured data. The description adds only the sort order ('newest first') and the paging mechanism, with no detail on caps, response shape, or behavior at offset boundaries — modest value beyond annotations, given an output schema exists.

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 short sentences with zero redundancy; the newest-first ordering and the filter/paging summary come before the sibling hand-off, so the most decision-relevant information is front-loaded.

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?

With annotations carrying safety, a full output schema, and 100% parameter coverage, the description only needs to convey scope, ordering, and routing — all of which it does. The remaining gap is minor: it never notes that offset paging can be inconsistent with the newest-first ordering, which matters for an agent iterating pages.

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 limit, offset, and created_after are already fully documented including ranges and defaults. The description restates the filter and paging intent without adding syntax or edge-case guidance (e.g., whether offset pagination is stable when new contacts arrive). Baseline 3 applies.

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 resource ('List CRM contacts') plus the default ordering ('newest first'), which immediately separates it from get_contact/find_contact. The final clause names the sibling that handles a different query shape, so an agent can pick correctly 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?

Explicitly routes name/stage/tag-style lookups to search_leads and states the pagination mechanism for this tool. It does not address the other plausible alternatives (find_contact, get_contact) or when not to use the created_after filter, so it stops short of full when/when-not coverage.

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