lekta

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

Annotations already mark readOnlyHint=true and destructiveHint=false, and the description reinforces that the site is never modified. It adds substantial context beyond annotations: plain GET as LektaBot plus Chromium render pass, robots.txt honoring, 5-30 s typical latency with 75 s hard limit, per-day quota consumption, and 15-minute caching behavior. There is no contradiction with the annotations.

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 what the tool does and its output, then gives concrete usage and exclusions, then cost/behavior. Every sentence adds operational information an agent needs; there is no filler or redundant restatement of the name.

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 carries the burden of explaining what the agent will receive: a readable verdict with a grade, ranked issues, and complete fixes. It also covers timing, quotas, caching, and robots.txt behavior. For a single-parameter tool, this is sufficient for correct invocation and result interpretation.

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 for the single url parameter is 100%, and the schema already explains that it must be an absolute http(s) URL of ONE page, not a domain or sitemap. The tool description adds little new parameter-level information beyond restating 'ONE page' and 'current state of a page', so the baseline of 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 states a specific action (fetches ONE page as answer engines do) and a concrete outcome (grades A+ to F across Access, Indexability, Answerability, Recency). It explicitly names sibling tools for contrast (lekta_report, lekta_fix_plan, lekta_diff), so the agent can distinguish this tool without opening any 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?

The description gives explicit 'USE THIS when...' guidance (current state or after deploying fixes) and explicit 'DO NOT use it for...' exclusions with named alternatives. This fully answers when to choose lekta_audit over lekta_report, lekta_fix_plan, or lekta_diff.

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?

Although annotations already declare readOnlyHint and idempotentHint, the description adds valuable behavioral context: 'COST: free, reads stored data only' and the limitation that no result should be expected with only one audit. This goes beyond the structured annotations and clarifies side-effect-free 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 front-loaded with the core purpose and then adds targeted usage and exclusion guidance. Every sentence serves a purpose: what it does, when to call it, when not to call it, and what it costs behaviorally.

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 single-parameter read-only tool with no output schema, the description covers the operation, expected output highlights, prerequisite conditions, and exclusions. An agent has enough information to decide when to call it and what to expect.

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 already documents the single 'url' parameter with 100% coverage, including the requirement of at least two stored audits. The description reinforces 'one URL' and the prerequisite of a fresh audit, but does not add substantial new parameter-level detail beyond what the schema provides.

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: 'Compares the two most recent stored audits of one URL: grade and score movement, which checks improved, which regressed.' This clearly distinguishes lekta_diff from its siblings and communicates exactly what the tool computes.

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 gives explicit positive usage: 'USE THIS after a deploy plus a fresh lekta_audit' and 'call it after re-auditing to prove a fix worked.' It also gives explicit negative constraints: 'DO NOT use it to compare two different URLs, and do not expect a result when only one audit exists.'

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 indicate readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds valuable behavioral context beyond those: it never fetches the page, reads stored data only, is free/quota-free, and returns nothing for unaudited URLs. There is no contradiction with the annotations.

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 transformation, then provides usage, limitation, and cost guidance in compact phrases. It is slightly redundant by saying both 'reads stored data only' and 'never fetches the page,' but overall every sentence earns its place and the structure is easy to scan.

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 single-parameter tool with strong annotations and no output schema, this description is complete. It explains what it produces, when to use it, what it cannot do, what happens for unaudited URLs, and the required next step (lekta_audit). No essential selection or invocation guidance is missing.

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 url parameter already includes a meaningful description: 'Absolute http(s) URL that was audited before.' The tool description reinforces that the URL must have been audited, but does not meaningfully extend the parameter semantics beyond what the schema already provides.

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 a specific verb and resource: it turns the most recent stored audit of a URL into an ordered work plan with expected point recovery, hardest-hitting fixes first. It also differentiates itself from measurement tools by explicitly warning 'DO NOT use it to measure,' and distinguishes itself from lekta_audit by noting it returns nothing if the URL was never audited.

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 gives explicit when-to-use guidance: 'USE THIS to decide what to change before touching the code.' It also gives a clear exclusion: 'DO NOT use it to measure — it never fetches the page,' and provides a fallback: call lekta_audit first if the URL was never audited.

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?

Beyond the readOnly, openWorld, idempotent, and destructive annotations, the description adds meaningful behavior: it reads stored state only, returns no fresh measurement, and is account-scoped. It also states cost and zero parameters, leaving no hidden operational traits.

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 compact, front-loads the core action in the first sentence, and uses clear directives ('USE THIS', 'DO NOT') and a COST line. Every sentence adds value and the structure is easy to scan.

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 zero-parameter read-only list tool, the description is complete: it states the account scope, the stored-state behavior, the included fields, and usage context. No output schema exists, but the description already names what the return contains.

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 is empty and the description confirms 'takes no parameters.' With zero parameters there is little to explain, so the baseline of 4 applies; the description adds no param-specific meaning but correctly signals there are no arguments.

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: 'Lists the sites saved on the authenticated Lekta account' and identifies exactly what data is returned (grade, score, scheduled-recheck setting). It also distinguishes the tool from a fresh audit by noting it 'reads stored state only.'

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 explicit when-to-use guidance: 'USE THIS to see what this account already tracks before auditing something new.' It also gives when-not-to-use boundaries: 'DO NOT expect sites from other accounts or a fresh measurement,' which routes the agent toward lekta_audit for fresh measurements.

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 disclose readOnlyHint and destructiveHint, and the description adds valuable cost/caching behavior: 'cached report is free, otherwise it spends one fresh-audit slot.' This goes beyond annotations. No contradiction with annotations; openWorldHint aligns with the fresh-audit caveat.

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?

Compact and well-structured: purpose is front-loaded, followed by usage guidance and cost note. Every sentence carries distinct information with no filler or repetition.

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 single-parameter read-only tool with no output schema, the description sufficiently explains the return format, usage context, and cost implications. Nothing an agent needs to select or invoke the tool correctly is missing.

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 the url parameter fully described as 'Absolute http(s) URL of ONE page.' The tool description adds no additional parameter-specific meaning beyond the schema, 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 resource and output format: the complete structured JSON audit report with every layer and check including status, evidence, and fix text. It explicitly contrasts with lekta_audit's shorter human-readable output, making the distinction clear even among multiple siblings.

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 explicit when-to-use guidance: 'USE THIS when a program (not a human) consumes the result, or when you need a field lekta_audit does not print.' It also states when not to use it: 'DO NOT use it for a quick human-readable verdict,' naming lekta_audit as the alternative.

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