AiGramX

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

With no annotations at all, the description carries the full behavioral disclosure burden. It does explain that posts are safety-moderated, rate-limited, and new accounts are held for review — meaningful behavioral disclosure. However, it doesn't fully detail outcomes (e.g., what happens on moderation failure, retry semantics) or clarify whether the resulting post is immediately visible.

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 one dense block of three sentences covering substantial ground efficiently. It is front-loaded with the core purpose and packs auth, eligibility, and moderation into a compact space, but the sentences are long and could benefit from structural separation (bullets or clearer clause boundaries) for scanability.

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 mutation tool with 6 parameters, no output schema, and no annotations, this description does substantial work: it covers the purpose, auth prerequisites, content eligibility constraints, contentSource semantics, and post-publishing behavior. Given the complexity, this is reasonably complete, though it could add return-type or error semantics.

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 only 33%, so the description must compensate. It does clarify the key contentSource parameter (AI_GENERATED vs ROBOTICS_DOCUMENTARY) and the aiEngine attribution requirement, which the schema enum alone wouldn't convey. However, several parameters (mediaUrls, category) get no semantic addition in the description, though the enum values are reasonably self-explanatory.

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 the action 'Post to AiGramX on behalf of your account' with a specific verb (post) and resource (AiGramX). It explicitly distinguishes itself from siblings like get_feed, get_post, get_profile, and search, which are clearly read-only retrieval tools, whereas create_post is the mutating write operation.

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 provides substantial usage context: it specifies the required auth mechanism (aigx_live_ API key on CREATOR tier), content eligibility rules (AI-generated with attribution OR robotics documentary photos), and moderation conditions. It doesn't name alternative tools explicitly, but the read-only sibling distinction is implicit, and the eligibility requirements give strong when-to-use guidance.

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?

With no annotations provided, the description carries the full burden. It discloses 'no authentication required' and that it's 'public,' which is genuinely useful behavioral info. However, it doesn't describe pagination behavior, rate limiting, what happens with limit exceeded, or the shape/format of returned posts. Some transparency but not comprehensive.

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 concise sentence that front-loads the core purpose, followed by the authentication note. Zero waste, every word earns its place. Appropriate length for a simple read tool.

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?

The tool has a simple schema (2 optional params, one enum), making it relatively straightforward. No output schema means the description could help by noting return shape, but doesn't. It also doesn't mention the mode default behavior or how limit interacts with paging. Given moderate complexity and 50% schema coverage with no annotations, the description is partially complete but leaves some gaps.

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 50% (mode has an enum+description; limit has none). The description adds no parameter-specific details beyond what the schema provides. The schema's mode enum already explains home vs trending. The description's 'public' framing adds some context but doesn't explain limit semantics or edge behaviors. Baseline 3 is appropriate given moderate coverage.

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?

Clear verb+resource: 'Read the public AiGramX feed of AI-creator and robotics posts.' It describes what the feed contains (AI-creator and robotics posts). It distinguishes from siblings somewhat by focusing on feed reading, though get_profile/search are clearly different. Doesn't explicitly contrast with get_post but the purpose 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?

'No authentication required' gives useful context about accessibility. However, there's no explicit statement about when to use this vs alternatives (e.g., when to use get_feed vs search, or get_feed vs get_post). The 'public' qualifier implies it's for public content, which is useful guidance, but exclusions are not 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?

No annotations are provided, so the description carries full burden. It states this is a read/safe operation ('Get') and limits to 'public' posts, which is useful. However, it doesn't disclose potential 404 behavior for non-existent posts, auth requirements for accessing public vs private content, or whether media URLs are returned inline. For a simple GET this is moderate but could be richer.

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 sentence, zero filler. Enumerates the returned content in parentheses compactly. Every word earns its place and the purpose is 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?

For a single-id retrieval tool with good schema coverage and no output schema, the description is reasonably complete. It tells the agent what it returns (caption, media, AI attribution, engagement). However, with no annotations, it never addresses error cases (e.g., non-public or non-existent post), pagination (not applicable here), or authentication. Adequate but not optimized.

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% since the single parameter 'id' has a description ('Post UUID'). The description reinforces that id refers to a post but doesn't add much beyond schema — it's a UUID format for identifying a post. Baseline 3 is appropriate when the schema already documents the parameter fully.

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?

Clear verb+resource ('Get a single public post') with scoping to 'public' and explicit content dimensions listed (caption, media, AI attribution, engagement). The word 'single' distinguishes it from get_feed (which lists multiple posts), and 'public' hints at access restrictions compared to other getters. Doesn't explicitly name sibling alternatives but produces enough clarity to differentiate.

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 'public' qualifier implies this works only on public posts, suggesting it's not for private content, but this is implied rather than explicit. No when/when-not statements, no alternatives named. For a retrieval tool with siblings like get_feed and get_profile, clearer guidance on when to use this specific getter would help.

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?

With no annotations provided, the description carries full burden for behavioral disclosure. The description only says the profile is 'public,' but doesn't disclose what fields are returned, whether an unknown username errors or returns empty, rate limiting, or authentication requirements. For a read-only retrieval tool, the 'public' label is helpful but minimal.

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 declarative sentence that accomplishes its job with zero waste. Every word earns its place, and the description is appropriately sized for a tool with one parameter.

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?

The tool is simple (1 parameter, no output schema, no nested objects), and the description covers the core function. However, it's missing useful context like what fields the profile contains, error behavior for nonexistent usernames, and how it differs from sibling tools like get_post or search. Adequate for a simple tool but not 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 description coverage is 0%, so the description must compensate for the single username parameter. It does partially by specifying the lookup mechanism ('by username'), which clarifies how the parameter is used. However, it doesn't add detail on username format, case sensitivity, or whether exact match is required. With only 1 parameter, the 'by username' phrasing adds meaningful value.

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 uses a specific verb+resource ('Get a creator's public profile') with a clear qualifier ('by username'). It's clear what the tool does, though it doesn't explicitly distinguish from siblings like get_post or search, which also involve retrieving public content.

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?

No context is provided about when to use this tool vs alternatives. There's no mention of how get_profile differs from search or get_post, nor any indication of when a user would prefer this tool. The 'public' qualifier hints at access scope but gives no explicit guidance.

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?

With no annotations provided, the description carries full behavioral disclosure burden. It adds the 'No authentication required' fact, which is valuable. However, it doesn't disclose what the search returns (mixed result types across posts, hashtags, creators), how results are ordered, or what pagination/maximums apply—beyond what the schema limit field already indicates.

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, efficient sentence that states the tool's purpose and adds the key prerequisite (no auth). No filler, no redundancy. Well 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?

This tool is relatively simple (2 params, no nested objects, no output schema). The description covers the basics—what's searched and auth requirements. However, with no output schema and no annotation coverage, the agent is left uncertain about the heterogeneous return shape (posts vs hashtags vs creators), which is an important missing detail for a mixed-type search 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 0%, so the description must compensate for the two parameters. The description's relation to 'query' is implied (the search term), but it adds no minimum length, no format guidance, and no clarification about the 'limit' parameter's role beyond what the schema defaults indicate. It doesn't explicitly map parameters to described behavior.

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 uses the specific verb 'Search' with a clear resource scope: 'AiGramX posts, hashtags, and creators.' It clearly states what is being searched and distinguishes it as a discovery/search tool among siblings like get_feed, get_post, and get_profile. It doesn't explicitly contrast with siblings, but the purpose 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?

The description notes 'No authentication required,' which is a useful prerequisite/usage note. However, it doesn't state when to use this vs alternatives (e.g., get_feed), nor does it mention that searching posts vs creators may return mixed result types. Context is implied but not fully specified.

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