np_count_spikes

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

There are no annotations, so the description must disclose behavioral traits. It does not mention whether this is read-only, whether it triggers stimulation, what the return value looks like, or any side effects. The term 'Closed-loop' suggests potential interaction with stimulation, but no details are provided. This lack of disclosure is a significant gap.

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?

The description is a single, concise sentence with no unnecessary words. It is front-loaded with the tool's purpose. However, it is somewhat cryptic due to the '_count_spike' phrasing and the dash/colon structure, which slightly reduces clarity. Still, it earns its place as a brief summary.

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 no annotations, the description should provide more context about return values and distinguishing features. It only states the basic counting function, omitting any mention of output format, comparison with siblings, or operational context. The sibling 'np_query_spike_count' makes this lack of differentiation particularly problematic.

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?

The schema already covers both parameters with descriptions (100% coverage). The description's 'N-ms window' loosely maps to 'window_ms' but adds no new detail beyond the schema. It does not clarify value formats, units, or interaction between top_k and window_ms. Baseline of 3 is appropriate since schema does the heavy lifting.

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 'spikes per electrode over an N-ms window', which clearly indicates the tool counts spikes per electrode within a time window. The action (counting) is implied by the verb in the tool name and the phrasing. However, it does not explicitly differentiate from the sibling tool 'np_query_spike_count', and the 'Closed-loop _count_spike' prefix is somewhat cryptic, leaving ambiguity about whether this is for closed-loop experiments only.

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?

The description provides no guidance on when to use this tool versus alternatives like 'np_query_spike_count' or 'np_query_spike_events'. It lacks any mention of scenarios, prerequisites, or exclusions. The only hint is 'Closed-loop', which implies a specific context but is not explained.

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