Let Agents In

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

Annotations already indicate read-only and idempotent behavior, but the description adds substantial context: return format details, performance metrics from a benchmark, the deliberate quietness, refusal patterns, and the distinction between 'silence' and empty category. It goes far beyond what annotations provide and does not contradict them.

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?

While the description is front-loaded with the main instruction and return format, it quickly digresses into an extensive evaluation methodology discussion (40 questions, 29/40 accuracy, etc.). This is a wall of text that could be trimmed to the essential usage and behavioral notes. Every sentence does not earn its place.

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, the description fully explains what the tool returns (vendors with date and evidence link, split by barrier status). It also covers input expectations, limitations, and how to interpret silence. It is complete enough for an agent to use correctly, even if overlong.

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 has only a basic description for the 'job' parameter, but the tool description expands significantly: it gives examples, explains how to phrase problems, notes that English is expected, and clarifies how different input shapes are handled. This adds meaning well beyond the schema field.

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 clearly states the tool's function: it takes a free-text problem description and returns measured vendors in that category, split by barrier outcomes, with dates and evidence links. It explicitly distinguishes itself from a recommendation tool, clarifying its actual scope. The title and description are aligned.

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 explicit usage instructions: 'Describe the problem in your own words,' notes the tool reads English, and warns that silence means it could not read the question. It also specifies when not to use it ('This is not a recommendation') and suggests naming the category when known. This is comprehensive guidance.

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?

The description discloses that the tool makes 16 deterministic HTTP checks, which aligns with the openWorldHint annotation indicating external side effects. It adds context about the scoring logic and that a permanent link is returned, going beyond the annotations. However, it could more explicitly state that HTTP requests are made to the submitted domain, but overall it is transparent enough for an agent to anticipate 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?

The description is three sentences, no filler, and front-loads the core purpose. Every sentence provides essential information: the scoring method, the scoring scale, and the output format. This is an appropriately sized and well-structured description.

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?

Given the tool has only 2 parameters, no output schema, and moderate complexity, the description covers the key aspects: what the tool does, how scoring works, and what the result includes (per-check breakdown with link). It is missing explicit mention of the external HTTP requests (implied by openWorldHint) which could affect agent planning, but still leaves agents reasonably informed for invocation.

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%, with both parameters (domain, format) fully described in the schema. The tool description does not add any additional semantic value beyond what the schema already provides for these parameters. Therefore, it meets the baseline expectation with no extra contribution.

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 clearly states the tool scores a domain across 5 funnel stages using 16 deterministic HTTP checks. The verb "scores" is specific, the resource "domain" is explicit, and the explanation of the scoring system (18 points, scaled) distinguishes it from the sibling tool find_providers, which likely searches for providers rather than assessing readiness.

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 implies usage for assessing a domain's agent readiness, but it does not explicitly state when to use this tool versus find_providers or any other alternative. No guidance on exclusions (e.g., when not to use) or prerequisites is provided, leaving the agent to infer context from the purpose alone.

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