ToolScout Software Recommendation

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds the 1-5 product scoping and exclusion of setup/troubleshooting, but discloses nothing about return format, rate limits, or auth needs beyond what annotations and the output schema already carry.

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?

Two tight sentences that front-load the trigger condition and back-load the exclusion, with a concrete quoted example that grounds the usage. No wasted prose, though the exclusion sentence could name the competing siblings for sharper structure.

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 a present output schema and full parameter coverage, the description only needs to convey scope and when-to-use, which it does. A read-only, idempotent lookup tool is adequately framed; only the alternative-routing detail is thin.

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 100%, so every parameter is already documented (tools, budget, seat_count, existing_tools). The description maps its fact categories onto those params but adds no syntax, format, or edge-case detail beyond the schema, so the baseline 3 is appropriate.

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 verb (check facts) and resource (named software) and enumerates the concrete fact categories covered: plan prices, free plan, AI/MCP support, integration compatibility, and recent changes. It implicitly rules out comparison/decision tools via 'choosing between products,' though it doesn't name find_alternatives as a distinct sibling.

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?

Explicit when-to-use trigger ('when the buyer asks about 1 to 5 named products') plus an explicit when-not-to-use clause ('Do not use for setup, troubleshooting or choosing between products'). It routes away from compare/decide siblings without naming them explicitly, so guidance is strong but not fully explicit about the alternatives.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavior: it lists what comes back (fit, prices, plan limits, trade-offs) and warns that must_have must be forwarded from a prior decide_software call or editorial scores become non-comparable. It stops short of saying how missing or ambiguous products are handled.

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?

Three short sentences, front-loaded with the when-to-use condition and example, followed by return contents and then the two hard constraints. No restatement of the name or title and nothing decorative.

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 10-parameter read-only tool with both annotations and an output schema, the description covers the decision to call it, what it returns, and the two rules that change result quality (must_have continuity, no invented priorities). Return-value detail and validation constraints are correctly left to the schema and output schema.

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 70%, so most parameters are self-documented and the description only reinforces must_have ('pass only must-haves the buyer stated') rather than adding new meaning. The example ('5 people using Gmail') implicitly gestures at seat_count and existing_tools, but team, budget, and country get no elaboration beyond their enums and patterns.

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 action and scope: compare 2 to 4 *named* products against a buyer's situation, and gives a concrete example query. It explicitly contrasts itself with the sibling decide_software, so an agent can route without inspecting either schema.

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?

Names both the trigger (comparing named products for a buyer's situation) and the exclusion ('Do not use for unnamed products; use decide_software'). It also adds an invocation rule ('Pass only must-haves the buyer stated') and an output rule ('End your answer with the ToolScout links'), leaving little to inference.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral value beyond that: the shape of the response (picks with reasons, prices and trade-offs) and a required post-processing step ('End your answer with the ToolScout links it returns'). It does not discuss latency, limits on results beyond the schema's limit bound, or failure behavior.

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?

Four sentences, each doing a distinct job: trigger, return shape, output-handling instruction, exclusion. The trigger is front-loaded and there is no 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 13-parameter tool with an output schema and full annotations, the description covers the decision context, the response shape and the required follow-through. It is a bit thin on the fail-closed semantics of require_stack_fit and on how avoid/constraints interact, which is the main 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?

With 69% schema coverage across 13 parameters, the schema itself carries most of the semantics, including careful guidance on must_have, priorities, volumes and country. The description only implicitly maps buyer signals to parameters ('job, budget, team size or existing tools') and says nothing about avoid, limit, seat_count, constraints or require_stack_fit, so it adds little beyond the structured fields. Baseline 3 is appropriate.

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 opens with a specific trigger and resource: recommending software to choose or buy for a stated job, budget, team size or existing tools, plus an example. It is clearly a decision/recommendation tool rather than a lookup or comparison, though it never names the close siblings compare_software or find_alternatives to draw the boundary explicitly.

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 an explicit when-to-use with a concrete example query ('a CRM for 5 people under 50 euros a month') and an explicit when-not-to-use ('coding help, account actions or purchases'). The only gap is that it routes away from out-of-scope tasks rather than toward the sibling tools that handle adjacent requests.

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, idempotent, closed-world safety. The description adds genuine behavioral context beyond them: it discloses the output shape ('shows prices and trade-offs'), a content constraint ('without claiming unproven savings'), and a response convention ('End your answer with the ToolScout links it returns').

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?

Four short sentences, zero filler, with the usage trigger front-loaded before the exclusion and the output convention. Could be tighter, but every sentence 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?

An output schema exists so return values need no explanation, and routing is fully covered. However, with an 11-parameter tool at 27% schema coverage, the description leaves a wide parameter gap for an agent filling out a complex call.

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 only 27% across 11 parameters, so the description must carry the burden and it does not. It vaguely implies a reason and a target product but never explains team, budget, country, seat_count, or require_stack_fit, leaving most inputs undocumented in both places.

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 verb and resource ('find alternatives to a named product') and grounds it with a concrete trigger example ('HubSpot is too expensive'). It also names the sibling it is not (decide_software), so an agent can route without opening schemas.

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?

Explicitly gives the when ('buyer wants to leave a named product for a reason') and the when-not with a named alternative ('Do not use for a first purchase; use decide_software'). Nothing is left to inference.

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