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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior beyond that: on no match it answers 'DeepStack has no formed side on …' and still returns up to three nearest items explicitly labeled as nearest — a fallback an agent could easily misread as real results. Return shape (canonical URLs) is also disclosed; pagination/rate limits are not, but are of low relevance here.

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?

One front-loaded sentence that opens with the trigger condition and then the output contract, with no redundant restatement of the name or title. Density is high and every clause (use-case, return shape, no-result fallback, ordering rule) carries information.

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 no output schema and only three parameters, the description does the heavy lifting: it enumerates what a hit contains, supplies canonical URLs, and explains the empty-result path. What it leaves unstated is how the different kinds relate (e.g. when to search 'sides' vs 'story'), but that gap is minor for a general search entry point.

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 100%, so query, kinds and limit are all documented in the schema, and the baseline is 3. The description corroborates the query semantics ('a company, a person or a question') and echoes the kinds via 'stories, sides, tests and entities', but adds no format, syntax or defaulting guidance beyond what the schema already provides.

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 states a concrete retrieval action ('returns the matching stories, sides, tests and entities with their canonical URLs') and the domain (AI economy), so the agent knows exactly what comes back. It separates itself from siblings only indirectly, via 'Use it first when the slug or name is not known', without naming deepstack_entity or deepstack_story as the follow-up, so differentiation stays partial.

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 gives explicit triggering conditions: where informed investors disagree on a topic, or a request for published analysis on a company/person/question. The sequencing rule 'Use it first when the slug or name is not known' is genuinely useful routing guidance. It stops short of naming the sibling to switch to once the slug is known, so the alternative is implied rather than stated.

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