Evolize

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), yet the description adds substantial context beyond them: the not_found semantics and their non-implication, that it inspects publicly reachable pages in a real browser with axe-core plus Evolize rules, and that it does not read source code so findings reference the rendered DOM. This is exactly the extra context the lower bar with annotations rewards.

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 purpose is front-loaded in the first sentence and each sentence carries useful information about behavior, return semantics, and scan mechanics. It runs long for a read-only getter, and the 'coding agent maps them to source' sentence is more advisory than necessary, but nothing is redundant 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?

With no output schema, the description usefully discloses the not_found return and that findings reference the rendered DOM rather than source lines. It stops short of describing the response shape or the meaning of limit/cursor paging behavior, but it is otherwise sufficient for an agent to call this correctly.

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 url, limit, and cursor are already documented with examples and ranges in the schema itself. The description adds no parameter-level detail beyond that, making the baseline 3 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 and resource ('Retrieve an EXISTING public Evolize accessibility assessment for a website') and immediately distinguishes itself from sibling scan_website with 'this starts no scan and creates no work.' An agent can route between this and the scan tools without opening any 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?

The 'EXISTING' emphasis and 'starts no scan' clause effectively tell the agent to use this when a report may already exist rather than to trigger a new scan, and it warns that not_found carries no implication about site quality. However, it never names the alternatives (scan_website, get_scan_result) explicitly, so the routing is implied rather than stated.

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, yet the description still adds real value beyond them: no scan starts, no refresh, no publication-state change, no quota consumption, so polling is safe. It also discloses the pending-state response shape (status + retry_after_seconds) and pagination contract, which no annotation covers.

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 tightly packed sentences, front-loaded with purpose, then safety/quota, then pending and pagination behavior. Every clause carries information an agent needs; nothing is 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?

With no output schema, the description compensates by naming the key return elements (status, retry_after_seconds, next_cursor, findings). Combined with the annotations and full schema coverage, an agent has everything needed to call and consume this tool correctly.

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 limit and cursor are already fully documented; the description reinforces scan_handle provenance and the cursor-to-next_cursor loop but adds no syntax or constraint beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Read the result of an Evolize assessment') and ties it directly to the sibling that produces the input ('started with scan_website, using the scan_handle it returned'). An agent can distinguish this from scan_website and get_public_report without opening a 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?

Gives clear context: use it after scan_website, poll it safely, and follow next_cursor to page through findings. It handles the pending case with retry_after_seconds. It never explicitly contrasts with the get_public_report sibling, so the routing guidance is strong but not fully exhaustive.

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 mark readOnlyHint=false and openWorldHint=true; the description goes well beyond them by disclosing that this starts real browser-based work, that results are retained and may become a public report, the 24h reuse default, refresh overriding it, and concrete rate bounds (3 executions/website/24h plus per-IP, per-domain and global limits). This is exactly the mutation/quotas context the annotations cannot 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?

The purpose is front-loaded and the sentence order (what it does, how to read the result, then policy) is logical. Mild redundancy: the 24h reuse-unless-refresh rule is stated twice, so not every sentence pulls full weight.

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?

Complete for a 2-param, no-output-schema tool: it explains the deferred-read pattern via get_scan_result, the creation semantics, the reuse/refresh tradeoff, and the applicable quotas. An agent has everything needed to call it correctly and set expectations about side effects.

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, but the description adds meaning the schema lacks: the concrete 24-hour reuse window that refresh=true bypasses and the 'newly executed work' guarantee. It adds little for url beyond restating reachability, keeping this from a 5.

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 ('Request an Evolize accessibility assessment of a publicly reachable website') and explicitly routes result retrieval to the sibling get_scan_result. An agent can distinguish it from get_scan_result and get_public_report without opening a 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?

Gives an explicit condition for refresh=true ('for example after deploying a fix') and points to get_scan_result for reading output, which is clearly implied as the read counterpart. It does not explicitly state when NOT to call this versus just fetching an existing report, so it falls short of full alternatives coverage.

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