AgenticWebScore

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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description adds domain-relevant behavior by clarifying the tool performs no scanning and reads from stored state. It does not cover failure behavior (e.g. no scan yet, unknown check id), which would be the remaining useful disclosure.

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 sentences, zero filler, with the core action and the non-scanning constraint front-loaded. Every clause earns 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?

For a two-parameter read tool with full schema coverage and no output schema, the description supplies the return format (markdown) and the granularity options, which is nearly everything an agent needs. The only omission is behavior when the host has no stored record or the check id is unknown.

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 the baseline is 3. The phrase 'or one check of it by check id' does confirm that omitting 'check' yields the full report, but that is already stated in the schema's own parameter description, so the marginal value is small.

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 (returns the markdown status report) plus the scope (a host's stored scan record, or a single check). The closing clause 'It starts no scan' explicitly separates it from the scan_site sibling, so an agent can route correctly without opening 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?

Clear context is given: this reads an already-stored record rather than triggering collection, which implicitly tells the agent to call it after a scan exists. It does not name get_score or list_checks as alternatives or state what to do when no record exists, so it stops short of explicit when/when-not 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuine value by confirming no scan is triggered and disclosing the error behavior when no record exists. It does not describe what the record contains, which keeps it from 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?

Three short sentences, each carrying distinct information: what is returned, what does not happen, and the failure mode. Front-loaded and free of waste.

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?

There is no output schema, so the description must carry the return-value burden, but 'stored scan record' is left largely undefined — no indication of fields, freshness, or shape. It is adequate for calling the tool correctly but leaves a meaningful gap about what comes back.

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% and the single 'host' parameter is fully documented with format examples in the schema. The description adds nothing beyond what the schema provides about the parameter, so the baseline 3 applies.

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 ('Return the stored scan record for a host') and distinguishes itself from the scan-initiating sibling by saying 'It starts no scan.' However, the name get_score versus the description's 'scan record' leaves slight ambiguity about whether the returned payload is a score or a broader record, and siblings get_report/list_checks are not addressed.

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 starts no scan' implicitly routes the agent to scan_site when fresh data is needed, which is a clear usage condition. It stops short of explicitly naming alternatives such as get_report or stating when a stored record is preferable to a report.

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 (readOnlyHint=true, openWorldHint=false), and the description productively adds return-shape and domain semantics: fields per check, how scored checks differ (part/tier/weight), and that unscored checks are worth 0 points. It doesn't say whether the list is static for rubric v0.9 or whether a different rubric version could appear, which keeps it from 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?

Three short sentences, front-loaded with the scope (60 checks, 5 dimensions) followed by the per-item shape and the scored/unscored scoring rule. No filler, no restatement of the title.

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 correctly takes on the burden of describing what each returned check contains, plus the 0-point rule for unscored checks. It is nearly complete; only rubric versioning/stability of the list is unaddressed.

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 takes zero parameters, so there are no parameter semantics to explain and the baseline of 4 applies. The description doesn't waste space on non-existent inputs.

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+resource ("List the 60 checks of rubric v0.9") and quantifies scope across 5 dimensions, so the agent knows exactly what it gets back. It does not differentiate itself from siblings like get_score or get_report, so it falls short of a 5.

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?

Usage is only implied: this is the enumeration step you'd call before scoring or reporting, and the note that unscored checks earn 0 points hints at the scoring relationship. No explicit when-to-use, when-not-to-use, or named alternative (e.g., 'use get_score to evaluate a single check') is given.

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 annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false. The description adds substantial behavioral context beyond that: the 6-hour stored-record reuse, fresh override, rate limits of 10 per minute and 3 concurrent scans, 60-second runtime, and the fact that timed-out scans still complete and are stored.

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 front-loaded with the core action and return record, then adds caching, rate-limit, and timeout details in a compact sequence. Every sentence contributes operational information needed to invoke the tool correctly.

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 there is no output schema, the description compensates by naming the returned record components: score, its two parts, level, per-check status, evidence, and fingerprint. It also covers the non-obvious async timeout behavior and rate limits, making the definition complete for this tool.

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 both parameters are already documented in the schema. The description reinforces that target is a public domain and explains fresh in terms of the 6-hour cache, but it adds only limited meaning beyond the structured schema.

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 a specific verb and resource: scanning a public domain and returning the full scan record with named components. It clearly distinguishes the tool's output scope from narrower siblings like get_score or list_checks, but it does not explicitly name those alternatives.

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 explains important usage behavior such as the 6-hour cache and the fresh override, plus rate limits and timeout handling. However, it does not explicitly say when to use scan_site versus get_report, get_score, or list_checks, so tool selection guidance is only implied.

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