ScoutRail

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the tool returns 'status', which gives some insight into the output, but does not elaborate on what statuses exist or any other behavioral aspects. Given the annotations, this is adequate but not rich.

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, succinct sentence that front-loads the core action and resource, then adds the status detail. Every word contributes value, and there is no redundancy or filler.

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 parameterless tool with no output schema, the description is sufficiently complete. It states what is listed (markets ScoutRail can scout) and what is included (their status). An agent can invoke it without further clarification, and the readOnlyHint confirms it is a safe read operation.

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 tool has zero parameters, so there is nothing to document. The schema description coverage is 100% (vacuously). With no parameters, the baseline is 4, and the description does not need to add parameter meaning. It correctly avoids inventing parameters that do not exist.

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 uses a specific verb 'List' and names the resource 'markets', adding the scoping context 'ScoutRail can scout' and the output detail 'and their status'. This clearly distinguishes the tool from the sibling 'scout_opportunities', which implies the latter is for actively searching opportunities rather than listing available markets.

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 does not explicitly state when to use this tool versus the sibling, nor does it provide any exclusions. The phrase 'can scout' implies a reference list, and the sibling name suggests an alternative, but the guidance is implicit rather than explicit. An agent would likely infer the right choice from naming, but no direct comparison is made.

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

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

Annotations already declare read-only/open-world behavior; the description adds that results are ranked, grouped, live, and include a recommended NEXT MOVE, and that re-calling is the way to get updates. This is helpful context, though it does not go into rate limits, auth, or staleness, so it stops short of a 5.

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 main purpose is front-loaded, followed by input guidance, return behavior, update policy, and examples. Every sentence contributes distinct information, including the external webhook alternative, without fluff.

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 two-parameter read-only tool with an output schema, the description covers how to invoke, what to expect, and how to refresh results. However, since sibling list_markets exists and the markets parameter accepts arbitrary codes, an explicit pointer to list_markets for available codes would have made the workflow fully discoverable.

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 the baseline is 3. The description adds value above the schema with natural-language usage ('Pass a short description of what the business sells or does'), concrete market code examples, and two JSON examples showing valid combinations.

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?

Opens with a specific verb and resource: 'Find live public tenders, grants, RFPs and buyers for any business, by country/market.' This clearly identifies what the tool does and, by focusing on opportunity discovery rather than market metadata, distinguishes it from the sibling list_markets tool without needing to name it.

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?

Gives direct invocation guidance: pass a short business description and optionally market codes. It explicitly handles update behavior ('call this tool again for the latest answer') and names the alternative (POST to the subscribe endpoint) with the condition that distinguishes backend apps from conversational agents.

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