Pulore App Planner

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description goes well beyond them: it discloses third-party data flow ('The address is sent to Google, which loads the page'), the no-side-effect guarantee ('does not edit the target website or submit forms'), the 20–40 second latency, and 12-hour result caching. Those latency and caching traits directly change how an agent should sequence and retry calls, which annotations cannot convey.

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?

Six sentences, front-loaded with the triggering conditions before the mechanics and the exclusions. Every sentence carries distinct operational value — engine, return payload, data-sharing, side-effect boundary, latency/caching, anti-patterns — 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?

Despite having no output schema, the description enumerates the return payload (performance/accessibility/best-practices/SEO scores, lab measurements, real-user CWV when available, top-impact fixes). Combined with stated latency, caching, and access limits, an agent has everything needed to decide, call, and wait 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 both parameters (url and device) are already fully documented in the schema, including the mobile default and the rationale that Google ranks on mobile. The description restates the public-page/no-credentials constraint on the URL but adds no new syntax, format, or interaction detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

Opens with a precise verb+resource ('how fast a public web page is') and enumerates the specific questions it answers (Core Web Vitals, Lighthouse, what to fix). It also names the underlying engine (Google PageSpeed Insights) and the exact score categories returned, so an agent can tell instantly this is a performance audit and not the case-study, booking, or scoping 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 triggers ('someone wants to know how fast... why it's slow... what to fix') and explicit exclusions ('Don't use it to check whether a site is up, for security scans or for keyword research'). It also states the eligibility boundary — public pages only, no localhost, no login-gated pages, no URLs with credentials — which is the main pre-call gate an agent must check.

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 behavior, and the description adds substantial context beyond them: it searches bundled case-study files, does not browse or modify external sites, and returns nothing when no project matches. It also previews the return payload (summary, link, timeline, team size, results).

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?

Front-loads the usage condition, then the action, then behavior and return shape. Every sentence carries distinct information with no repetition or 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 single-parameter, closed-world search tool with no output schema, the description covers trigger, matching logic, return values, no-match behavior, and boundaries. Nothing an agent needs in order to call it 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 coverage is 100%, so the schema already defines the single query parameter fully. The description still adds value by explaining what the query is matched against (industry, platform, services, technology tags), clarifying expected input semantics beyond 'topic words'.

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 ('Finds published Pulore case studies related to a topic') and scopes it to Pulore's own work, which cleanly separates it from siblings like audit_website_speed or scope_software_project. An agent can identify the tool without opening the 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 trigger ('only when someone asks about Pulore's own work or experience') with a concrete example, plus a clear exclusion ('Don't use it to find examples of other companies' products'). No sibling competes for this use case, so the absence of a named alternative is not a gap.

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?

Crucial behavioral information is provided, such as that the tool 'makes no request to Cal.com and does not create or reserve a booking.' This manages agent expectations regarding the actual interaction with the external service and defines the link as local data preparation rather than an API call.

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 definition is perfectly sized, clear, and structured logically: when to use it, how it works, and what it definitely doesn't do.

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 100% schema coverage and the annotations, the description provides all necessary contextual boundaries (local vs. live) needed for the agent to confidently select and invoke the 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?

While the schema description is already excellent, the text reinforces that the parameters (name, email, note) are used to pre-fill a booking form and doesn't imply a backend reservation, adding practical context to the schema fields.

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 provides a specific function: building a local booking link for Pulore's Cal.com page. This is highly specific and distinct from siblings like project scoping or case study finding.

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 provides a crystal clear trigger: 'Use this only when someone asks to talk to Pulore or book a call with them.' This defines the boundary perfectly.

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/openWorld=false, and the description adds substantive context beyond that: the plan is computed locally from fixed estimation tables, no project is saved, no external service is called, hours are priced at $100–$150/hr, and the output is a planning range rather than a quote. Those are exactly the caveats an agent must relay to a user.

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?

A single dense paragraph that is front-loaded with the use case and then layers output, method, and exclusions in a logical order. It is long, but nearly every clause carries information; the pricing sentence is the only part that could be trimmed without losing selection-relevant meaning.

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 fully by describing the returned plan's contents (effort ranges, team, timeline, phases, stack, budget). Combined with the 100%-covered schema and the read-only annotations, an agent has everything needed to call it and set user expectations 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 the baseline is 3, but the description adds handling guidance the schema does not: map the user's idea onto the closest enumerated features and disclose the mismatches in the reply. It does not otherwise explain individual parameters, so it stops short of 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?

The description names a specific verb and deliverable ('scope' → 'rough plan with effort ranges for each feature, the team, a timeline range, phases, a suggested stack and a budget') and enumerates the triggers ('app, website, SaaS, marketplace, internal tool, AI feature or MVP'). It is unmistakably distinct from siblings like audit_website_speed or get_pulore_booking_link.

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 condition ('someone wants to know what it would take to build a software product') and explicit exclusions ('Don't use it for projects that aren't software (like renovations, events or business plans), for task or project management, or to write code'). It also instructs the agent on partial-fit handling: map the idea to the closest features and state what doesn't fit.

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 annotations, it discloses the fixed external recipient, irreversibility by this tool, payload privacy, 24-hour duplicate suppression, and per-address daily throttling. The statement that the email contains only the supplied fields and never the conversation is especially valuable for a consequential open-world operation.

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 usage gate and concrete action come first, followed by approval, privacy, duplicate handling, and rate limiting. Although it spans six sentences, each supplies distinct operational information 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?

Together with the fully documented flat schema and annotations, the description supplies what an agent needs to select and safely invoke the tool: trigger conditions, consent requirements, recipient, consequences, content boundaries, and repeat-send behavior. The absent output schema is not a material invocation gap, though the exact daily cap remains vaguely stated as 'a few briefs a day.'

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%, and the description does not add substantial per-parameter formats or meanings beyond that schema. Its preview, approval, and fields-only requirements mainly govern invocation and overall payload scope, so the high-coverage baseline of 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?

The description states a specific action and resource: sending a project brief as an external email through Resend to Pulore's fixed inbox, hello@pulore.com, so the team can reply. This clearly distinguishes it from the audit, case-study, booking-link, and project-scoping 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?

It gives an explicit eligibility condition: use only when the person has specifically asked to contact Pulore or send their project. It also adds a mandatory pre-invocation workflow—show the recipient and every field, then call only after approval.

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