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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description still adds substantive behavioral detail beyond them - traversal skips node_modules, Pods, .git, .dart_tool, .gradle and hidden folders, and never follows symlinks. It does not discuss limits on scan time or permission failures, keeping 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 dense sentences, front-loaded with the core action and result shape, followed by usage guidance and then exclusion rules. No filler and nothing that could be dropped without losing 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-value structure need not be explained. Combined with full parameter documentation and explicit read-only/traversal behavior, the definition gives an agent everything needed to call it 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% and all three parameters (limit, platform, directory) are documented in-schema with defaults and enums, so the baseline is 3. The description confirms platform/variant and ordering semantics but adds no syntax or default detail the schema lacks.

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 (search) plus resource (Android .apk / iOS .ipa build artifacts) and even the result ordering and fields returned. It is easily distinguishable from siblings like list_builds and get_build, which operate on records rather than scanning a filesystem.

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 triggering condition: use when the user wants to upload 'the latest build' and the output path is unknown. That is clear context for invocation, though it does not explicitly name or exclude the sibling tools (list_builds, upload_build) as alternatives.

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, openWorldHint and destructiveHint=false, so the trailing 'Read-only.' merely restates structured data. The field enumeration also duplicates the output schema, so the description adds essentially no behavioral context beyond what the agent already has.

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 compact sentence with the key identifier and purpose front-loaded and no filler. The long field list is tight but partly redundant given the output schema, keeping it just short of ideal.

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 an output schema present and 100% parameter coverage, the agent has everything needed to call this correctly; the description is complete on inputs and outputs. Only the when-to-use-vs-siblings routing is missing, which is a minor gap for a simple read 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%, and the schema already explains that build_id comes from upload_build or list_builds and that app_id speeds up the lookup. The description contributes only an implicit mention of build_id, 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 with explicit scope ('Get one App Dropper build by its build_id') and enumerates the fields returned, so an agent can distinguish it from list_builds and find_builds 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?

The singular 'one build' and the 'by its build_id' phrasing imply this is the direct-lookup tool, but the description never explicitly contrasts it with find_builds or list_builds, nor states when to prefer one over the other. Usage is inferable but not spelled out.

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 and openWorldHint, so 'Read-only' is partly redundant. The description nonetheless adds real behavioral context beyond the annotations: results are filtered by the token's upload permissions, which explains why an app the agent 'knows' exists may be absent.

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, no filler, with the core purpose and the token-scoping constraint front-loaded before the use-case guidance. 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?

A no-parameter, read-only list tool with a full annotation set and an output schema. The description covers purpose, token scoping, intended uses, and downstream handoff, so nothing needed to invoke 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?

The tool takes zero parameters, so the baseline is 4. The description adds value by describing the shape of each returned entry (app IDs, bundle IDs, public install pages), which goes slightly beyond the empty input 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?

States a specific verb and resource ('List the App Dropper apps') and scopes it precisely to what 'the configured token can upload to'. It also enumerates the salient return fields (app IDs, bundle IDs, install pages), so an agent distinguishes it from find_builds/list_builds immediately.

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?

Explicitly states two use cases: answering which apps are available, and obtaining an app_id to feed list_builds. That is clear routing guidance, though it names a downstream consumer rather than an alternative tool for the same job, and gives no exclusion conditions.

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=true, so the safety profile is fully covered; the description's 'Read-only' merely repeats it. It does add real behavioral context not in annotations (newest-first ordering, install URL presence), but nothing about pagination, limits behavior, or empty 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?

Two tightly written sentences that front-load the resource and ordering, then the usage examples. The trailing 'Read-only' is redundant with the annotations and slightly dilutes an otherwise waste-free description.

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 an output schema present, the description needn't document return fields, and the optional app_id/token-scoping rule is handled by the schema. Ordering and use cases are covered; only edge cases like pagination or result limits are unaddressed, which is minor for a simple list 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 (limit and app_id) are already fully documented in the schema, including the one-app token fallback. The description adds no syntax, default, or boundary detail beyond what the schema provides, 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+resource (list an App Dropper app's recent builds) plus ordering ('newest first') and the fields returned, which implicitly separates it from find_builds (search) and get_build (single build). However, it never names those siblings, so the differentiation is inferred rather than explicit.

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 concrete when-to-use context with example questions ('what were the last builds I sent') and a task goal ('find a previous install link'). It does not state exclusions, e.g. that a known build should go to get_build or that filtered search belongs to find_builds.

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 only flag the generic profile (not read-only, open-world, non-idempotent). The description goes well beyond them: it discloses that the file is sent to App Dropper, published as the newest build of its app matched by bundle ID, that an unknown bundle ID creates a new app subject to token permissions, and that testers are notified by email and push. Timing ('a few seconds to several minutes for large builds') is also surfaced, which materially affects agent 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?

Front-loaded with what the tool does and what it returns, then usage, side effects, timing, alternatives and boundaries in that order. Every sentence carries distinct operational information with no filler or repetition of the schema.

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 an open-world, non-idempotent upload tool this covers everything an agent needs: conversion-checking scope (apk/ipa only), publication semantics, tester notification, latency expectations, the prerequisite fallback to find_builds, and explicit non-goals. Return values are additionally backed by an output schema.

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 all three parameters (tag, file_path, release_notes) are already documented in the schema, including defaults, length limits and the local-path-only rule. The description adds no additional parameter-level detail, so the 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?

States a precise verb+resource ('Upload a local Android .apk or iOS .ipa to App Dropper') plus the processing wait and the returned fields (app name, version, build number, install URL). This clearly distinguishes it from read-only siblings like find_builds, list_builds, get_build, list_apps and whoami.

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?

Explicitly names the triggering user intents ('asks to upload, share, send or distribute a mobile build to testers') and routes to the alternative when preconditions aren't met ('If the path is unknown, call find_builds first'). It also states a boundary — 'Does not build, sign or re-sign the app' — so the agent knows not to reach for it for build tasks.

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, so the safety profile is covered; the description adds non-obvious context, notably that the token itself is never revealed and which credential attributes (name, location, expiry, app scope) are exposed. It does not discuss caching or what happens when not signed in, so it falls just short of 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?

Two sentences, front-loaded with the status check and its output, then the usage trigger. Every clause carries information; 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?

An output schema exists, so return-value syntax is already handled structurally, and the description still summarizes the meaningful fields. With zero parameters and full annotation coverage, nothing essential is missing for correct invocation.

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 no parameters, which per the rubric anchors this dimension at a baseline of 4. There is nothing further a description could add.

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: checks sign-in status for App Dropper and enumerates exactly what it reports (credential name, source, expiry, app coverage). It is clearly distinguishable from the sibling build/app tools, which all operate on builds or apps rather than the server's own credential.

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 conditions: 'Use to debug setup or when another App Dropper tool reports an authentication problem.' That names both the proactive and reactive trigger, leaving nothing to inference.

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