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

With no annotations, the description carries the full burden, and it does earn credit for disclosing 'Read-only.'. Beyond that it says nothing about whether stats are real-time or snapshot, whether results are scoped strictly to one search_id, or what happens with an invalid/unknown search – all relevant for a mutation-free analytics read.

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?

Very short and front-loaded with the read-only flag, which is good, but it is telegraphic noun-list prose rather than clear sentences. It is not bloated, just under-structured.

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?

No output schema and no annotations mean the description has to explain both behavior and return shape; it lists metric categories, which partially stands in for an output schema, but leaves the key scoping parameter undocumented. For a two-param analytics tool this is insufficient.

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 0%, so the description must compensate, yet the only parameter detail it gives – '(7, 14 or 28 days)' – merely restates the enum already in the schema. The required search_id (UUID of which search, active vs paused?) is left entirely unexplained.

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?

The description enumerates what data comes back (contact totals, by role, top companies, daily series, credits spent) which implies a stats/reporting tool, but it never states a verb or an object scope, so the agent must infer it reads stats for a search. It offers no differentiation from near-neighbours like sdr_signal_stats, sdr_people_group_counts, or sdr_overview, all of which could plausibly return similar aggregate numbers.

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 call this versus sdr_overview, sdr_signal_stats, sdr_people_group_counts, or get_analytics_sdr. No prerequisites are given either, such as whether the search must exist or be activated before stats are populated.

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