UGT: Use the Geek Thing

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered by structured data. The description adds only the omit-to-get-all behavior, which is already implied by the schema's optional param. No return shape, auth, or rate-limit context is added, but an output schema exists so that is less critical.

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?

It is a single sentence with no padding, but it is a run-on that chains install instructions, AI app connection, Claude Desktop, and recipe runners together. The final clause is confusing rather than clarifying, so brevity comes at the cost of parseability.

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?

Complexity is low: one optional enum parameter, full annotations, and an output schema, so the description does not need to explain return values. What is missing is a plain statement of what the returned line actually is and why an agent would call this versus reading setup docs. Adequate but not fully self-sufficient.

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 enum values are self-explanatory platform identifiers. The description restates the schema's 'omit to get every one' note rather than adding new semantics such as what the returned install line contains or how platform detection should be done. Baseline 3 applies when the schema carries the parameter meaning.

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: get the single install line for UGT per platform, plus the Claude Desktop variant. The intent is legible and clearly distinct from the sibling tools (recipes, projects, files). It stops short of naming siblings, and the trailing clause 'what each computer runs recipes in' muddies whether it returns install commands or recipe-runner info.

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?

Provides guidance only for the optional parameter ('Omit the computer to get every one'), which tells the agent how to widen the call. There is no explicit when-to-use framing against alternatives and no prerequisites, though the sibling tools cover obviously different resources so no routing conflict arises.

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, and closed-world, so safety is covered. The description adds that recipes are 'verified for one job' and that the result 'always says what to do next', which hints at the payload's nature. It stops short of detailing what the response contains or how a project with no recipes behaves.

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, front-loaded with the action, which is good. However, 'Get how UGT runs one GitHub project' is jargon-heavy and the closing clause about every project working with UGT reads as promotional padding rather than actionable information.

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?

An output schema exists, so return values need not be explained, and the tool is a simple single-parameter read. The description covers the essential shape of the call and result. Minor gap: the undefined acronym 'UGT' assumes prior context.

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% for the single parameter, so the schema already documents the owner/repo or link format. The description restates that same format ('by owner/repo or its link') without adding validation rules, normalization behavior, or edge-case handling. 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: get the recipes shared for one GitHub project, addressed by owner/repo or link. The phrase 'the recipes people have shared for it, each verified for one job' makes the returned content concrete. It does not explicitly contrast with siblings like get_recipe or search_recipes, but the 'one project' scope is clear.

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: call it when you have a specific project and want its recipes. There is no explicit when-to-use versus search_recipes or get_recipe, and no stated prerequisites or exclusions. The alternative-routing work is left to the agent.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds the content scope a caller can expect (inputs/outputs, what persists after a run, settings, reachability, tested locations, files), which is useful context beyond the annotations, but it omits lookup-failure behavior for an unknown recipe ID.

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?

One front-loaded sentence with a long but readable enumeration of returned facets; every item earns its place by previewing the payload. No filler, though the list is dense enough to verge on a run-on.

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 one-parameter read-only lookup with annotations and an output schema, this is close to complete: it tells the agent what the response will contain and that the tool is safe and idempotent. The only gap is the absence of any failure or not-found behavior.

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%: the single `recipe` parameter has a documented owner/repo/task format, a regex pattern, and an example. The description adds nothing about the parameter, which is acceptable given the schema already carries the full 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?

States a specific verb and resource ("Get one recipe in full") and enumerates the facets it returns, which distinguishes it from search_recipes. It stops short of naming a sibling outright, but "in full" signals the detail-level contrast with search and file-level reads.

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: "in full" and "every file it runs" suggest this is the whole-recipe view rather than a search (search_recipes) or a single-file read (read_recipe_file). There is no explicit when-to-use or when-not-to-use statement, and no prerequisite or error condition mentioned.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only that the call returns file contents for a recipe it runs; it says nothing about what happens when the path is not among the recipe's files or whether content is truncated for large files.

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 front-loaded sentence with zero filler: verb, resource, concrete examples, and purpose in that order. Nothing is redundant or padded.

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, an output schema, and annotations covering safety, the description supplies enough to call it correctly. A note on error behavior for invalid paths would make it complete.

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 both parameters are documented in the schema, so the baseline is 3. The description's file examples give a sense of what a valid `path` looks like, but it adds no syntax or format detail beyond the schema's 'as the recipe lists it' constraint, and says nothing extra about the `recipe` ID parameter.

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 one of a recipe's files') and concretizes it with examples (compose.yaml, Dockerfile, recipe.json) plus the intent ('to see exactly what it runs'). It is clearly distinguishable from search_recipes or get_install, though it never explicitly contrasts with the closest sibling, get_recipe.

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 implied by 'to see exactly what it runs', which suggests inspecting file contents rather than recipe metadata. However, no alternative is named and there is no statement of when not to use it, e.g. 'use get_recipe for metadata only'.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description is consistent with it. What the description adds is domain framing — that a recipe is a verified single-project/single-job procedure — not behavioral detail such as result ordering, ranking, or what happens with very short queries. Nothing contradicts the annotations, but little is added beyond 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?

The first sentence is long and cluttered with a parenthetical example list, and the trailing definition of 'recipe' is explanatory context rather than actionable guidance. The core actionable content (what to search by, and the omit-for-newest behavior) is buried in the middle rather than front-loaded.

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 only two optional parameters and an output schema in place, the agent has everything needed to call the tool: what it searches, how to phrase the query, what omitting the query does, and a definition of the returned entity. The only remaining gap is sibling routing, which is a usage concern rather than a completeness one.

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 description restates the query semantics already present in the schema ('search by what the user wants done or by a project's name, or omit the query to list the newest recipes') and says nothing at all about the limit parameter.

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 concrete verb (find/search) and resource (recipes of how to accomplish a job with open-source GitHub software), with concrete example domains (subtitles, CAD, video-to-Markdown). It implicitly separates itself from the get_* siblings by framing the tool as discovery rather than retrieval of a specific item. The undefined acronym 'UGT' and the roundabout phrasing 'find how UGT gets a job done' keep it from being a crisp verb+resource statement.

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 tells the agent how to drive the query — search by user intent or project name, or omit it to list newest recipes — which is genuine usage context. However, there is no guidance on when to prefer this over its siblings (get_recipe, get_project, get_install), nor any exclusion such as 'use get_recipe once you know the exact recipe'.

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