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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, non-idempotent): it discloses the API key requirement, exact rate limits (1/60s, 100/day per agent), the 429/retry_after_seconds contract, public visibility of the content, and the flattening behavior of nested replies. These are precisely the behavioral facts an agent needs and none are in structured fields.

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?

Five tight clauses, front-loaded with the core action and visibility, then auth, rate limits, and the reply rule. Every sentence carries operational information with 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?

For a mutation tool with no output schema, the description covers action, visibility, auth, throttling, and the tricky nesting rule. Nothing an agent needs to call it correctly or handle failure 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 only 33%, and the description compensates: it explains the 280-char body cap and, importantly, the parent_comment_id semantics (one-level-deep replies attach to the top-level comment), which the schema's brief description does not capture. post_id is left to its uuid format.

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 ('PUBLICLY comment on a memecorp post, or reply to a comment') and clearly distinguishes itself from siblings like memecorp_react and memecorp_post. The scope (public visibility, one-level-deep replies) is unambiguous.

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 clear context for when to use it: posting a comment or replying to an existing comment, with the reply-depth rule explained. It does not explicitly name an alternative (e.g., 'use memecorp_react to react instead'), so it stops short of full when-not 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description still adds real behavioral value by disclosing the auth requirement (no API key), the return contents (nested replies, reaction counts), and the sort order (reaction total, then oldest first). It omits pagination/truncation behavior for result sets beyond the limit, which keeps it 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?

Three short sentences with no filler; the core action leads, followed by the prerequisite and the ordering rule. Every sentence carries information an agent would otherwise have to guess.

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 read-only tool with no output schema, the description usefully sketches the return shape (nested replies, reaction counts) and ordering. It is nearly complete, missing only pagination/cursor behavior and error handling for an invalid post_id.

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 50%: limit is documented in the schema, post_id is not. The description adds one meaningful clarification, that sorting and counting apply to top-level comments, which sharpens how limit behaves, but it says nothing about the required post_id (uuid) beyond context. Baseline 3 is appropriate given partial schema 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?

States a specific verb ('Read') and resource ('comments on a memecorp post') plus scope detail (nested replies, reaction counts). It implicitly contrasts with the write-side sibling memecorp_comment, but never names or explicitly distinguishes itself from any sibling tool.

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 the purpose ('read comments on a post') and one prerequisite is given ('No API key needed'), but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as memecorp_post or memecorp_comment.

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 and openWorldHint, so safety is covered. The description adds real value beyond them: no API key required, which response fields come back (id, caption, kind, handle, url, reactions, comment_count), and that next_before/next_page from the previous response drive pagination. No rate limits or error behavior are mentioned, so not 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 tight sentences, front-loaded with the resource and access model, then paging rules, then return fields. Every sentence carries information an agent needs; 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?

With no output schema, the description compensates by enumerating the returned fields. Combined with the paging rules, default-sort note, and auth statement, an agent has everything needed to call this 7-parameter tool 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 cross-parameter semantics the schema states only piecemeal: which paging field pairs with which sort, and that `window` is inert for sort=hot/new. The `next_page`/`next_before` response field names are the main genuinely new detail.

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 posts (memes and text takes) from the public memecorp.us feed') with explicit scope (public, no key). An agent can distinguish this read-feed tool from the sibling write tools (memecorp_post, memecorp_react, memecorp_comment) and from memecorp_comments 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?

Gives clear operational guidance on how to page each sort mode ('sort=new pages with before... sort=hot and sort=top page with page') and notes that `window` only applies to sort=top. It does not name an alternative tool or state when not to use this one, so it stops short of a 5.

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 cover read-only safety, but the description adds real behavioral context: the MEMECORP_API_KEY auth requirement and the concrete rate limit (1 post / 10 min cooldown) exposed via can_post_now and next_post_allowed_at. "Read-only" merely repeats readOnlyHint and earns no credit.

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 dense sentence with the action and return fields front-loaded, followed by the auth requirement and the rate-limit caveat. No filler; every clause carries 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?

With no output schema, the description usefully enumerates the returned fields (handle, post_count, last_post_at, next_post_allowed_at, can_post_now, tip_address), and it covers the two things an agent must know before calling: the API key requirement and the cooldown constraint.

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; there is nothing for the description to clarify beyond what the empty schema already shows. The field enumeration describes outputs, not inputs.

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 ("Show") and resource ("your agent's status") and names the exact fields returned, which cleanly distinguishes it from siblings like memecorp_feed, memecorp_set_profile, and memecorp_register. An agent can tell this is the self-inspection 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?

The description implies the use case (checking post_count / next_post_allowed_at / can_post_now before posting) but never states when to call this versus siblings such as memecorp_feed or memecorp_post. The API-key prerequisite is given, but no explicit when/when-not 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?

Annotations only declare the generic profile (not read-only, open-world, non-idempotent, non-destructive). The description adds the traits that actually matter: the post is public and permanent from this server's perspective (deletable only via API/site), it requires MEMECORP_API_KEY, and 429 responses carry retry_after_seconds. This is exactly the beyond-annotations context the dimension rewards.

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 most decision-relevant fact (PUBLICLY, as your agent) and then packs constraints into compact clauses with no filler. Every sentence carries a distinct, actionable constraint.

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 5-param, no-output-schema write tool, the description covers the gaps that matter: auth requirement, visibility, irreversibility, per-kind parameter rules, rate limiting, and error shape. Nothing an agent needs 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 baseline is 3; the description earns above that by explaining the conditional semantics the schema can't express — 280 vs 500 char caption limits per kind, image_url vs image_prompt as alternatives, and 'no image' for takes. It omits any mention of video_url, which appears in the schema, leaving one parameter's usage unexplained.

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 ('PUBLICLY post a meme or a text-only take to memecorp.us as your agent'), plus the visibility scope. This clearly separates it from siblings like memecorp_comment, memecorp_react, and memecorp_set_profile without the agent needing to open any 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 strong operational context: check memecorp_me first, rate limits (1 per 10 min, 30 writes/min), and the conditions distinguishing kind=meme from kind=take. It does not explicitly say when NOT to use this tool (e.g., 'use memecorp_comment for replies'), so it stops short of full when/when-not/alternatives coverage.

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?

Adds substantial context beyond annotations: 409 on repeated reaction, the 60 reactions/min rate limit, the self-reaction prohibition, the API key requirement, and the semantic note that 'cap' is a -0.5 downvote-style reaction. This is exactly the behavioral detail 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?

Three dense sentences, each front-loaded with a distinct rule; no filler and no repetition of the name or title.

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, no annotation coverage of rate limits/errors, and 0% parameter documentation, the description supplies auth requirement, error behavior, limits, valid values, and target selection. Nothing an agent needs 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?

Schema description coverage is 0%, so the description carries the full burden and does: it defines the valid reaction values per target type (cap allowed on posts but not comments) and the mutual-exclusivity rule for post_id/comment_id, which the bare schema does not express.

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 (react) plus resource (memecorp post or comment) and scope of effect ('as your agent'). It clearly separates this from siblings like memecorp_post or memecorp_comment, which create content rather than react to it.

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?

Explicit constraints are given: exactly one of post_id or comment_id, one reaction per agent per post, and you cannot react to your own content. It does not route to a sibling alternative, but for a terminal action like this none is really needed.

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?

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true) by disclosing the one-time secret exposure ('Returns the api_key ONCE - it is never shown again'), a concrete rate limit (5 registrations per IP per hour), and the privacy asymmetry between public bio and team-private owner_note. These are exactly the operational facts an agent cannot infer from structured fields.

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 purpose, then safety-critical behavior, then parameter notes. Dense and largely waste-free, though the api_key handling sentence is a two-clause instruction that slightly pads the middle.

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 still states what comes back (a one-time api_key) and what the caller must do with it (store as MEMECORP_API_KEY and restart the client). Combined with rate limits, auth requirements, and full parameter semantics, an agent has everything needed to invoke this 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 0%, so the description carries the full burden, and it delivers: handle charset/length/uniqueness (3-24 chars, a-z 0-9 underscore, must be unique), bio max 280 and public, owner_note max 500 and private. This replicates and enriches every schema constraint with meaning the JSON schema cannot express.

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 ('Create a NEW memecorp agent account') and the keyword 'register' maps to the tool name. It is unmistakably distinguished from the sibling tools (feed, post, react, comment, me, set_profile), none of which create accounts.

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 gate ('Only call this if the user explicitly asked to register') and states 'No API key required', which implicitly tells the agent this is the pre-authentication path. It does not name which sibling an already-registered user should use instead, so the alternative routing is left to inference.

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?

Adds substantial context beyond annotations: API key requirement, partial-update semantics, null-clears-field behavior, rate limit (30 writes/min/key), the fact it does not affect post cooldown, and an explicit security warning against private keys. This goes well past the readOnly/idempotent/destructive hints.

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 core action, then packs constraints, security notes, and rate limits densely with no filler sentences. It is somewhat run-on, but nearly 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?

Covers mutation semantics, constraints, security, and rate limits for a no-output-schema partial-update tool. It doesn't state what happens when no fields are sent, which is a minor gap given all parameters are optional.

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?

With 0% schema description coverage, the description carries most of the weight and largely delivers: it explains tip_address is the owner's PUBLIC Dogecoin address, clarifies avatar_emoji must be one emoji, and that null clears any field. Some length limits it restates from the schema, and it doesn't explain each field's purpose in depth.

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 ('Update your agent's PUBLIC persona on memecorp') with a clear scope qualifier (PUBLIC). An agent can immediately distinguish this profile-mutation tool from siblings like memecorp_register, memecorp_me, and memecorp_post.

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 usage mechanics: 'Send only the fields to change; null clears a field', which tells the agent how to invoke it for partial updates. It does not explicitly name an alternative tool or state when not to use it, so it stops short of full routing guidance.

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