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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so safety needs no repetition. The description adds genuinely new behavioral context: the data source (Job Spotter users who track applications), the operational definition of 'answer' (interview, offer or rejection), the inclusion of a wait-time measure, and a disclosure threshold of 5 tracked applications that suppresses small samples.

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?

Compact and front-loaded: the metric is stated first, then the user question it answers, then the data provenance and caveat. The opening repeats the title verbatim, which is mild waste, but every remaining clause 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?

For a single-parameter, no-output-schema tool this covers what an agent needs: what the number means, its source, the wait-time companion metric, and the 5-application disclosure floor. It stops short of saying what is returned below that floor (empty result vs. explicit suppression), which is the one remaining gap.

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?

One required parameter with 100% schema description coverage, so the baseline is 3. The description says nothing about the `company` argument beyond what the schema already documents (the example 'Monzo'), giving no extra detail on matching behavior or name format.

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 metric on a specific resource: the share of applications an employer answered and the usual wait time, sourced from Job Spotter user data. An agent can tell what it returns without opening the schema. However it never distinguishes itself from the closest sibling, jobspotter_company_lookup, which also takes a company.

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 line 'For "do they actually reply?"' frames the user intent (assessing responsiveness after applying) but is the only usage cue. There is no explicit when-not guidance and no routing to alternatives such as jobspotter_company_lookup or jobspotter_connection_score for related employer questions.

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