Read-only keyword opportunities: terms tracked competitors VISIBLY use that this app doesn't target and doesn't rank top-50 for, sorted by winnability. Inferred from competitor name/subtitle only — never their ranking algorithm.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | App name, App Store URL, numeric id, or bundle id | |
| country | No | ISO country storefront, e.g. US | |
| bundleId | No | Exact bundle id (skips resolution) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive, and the description reinforces that with 'Read-only.' It goes beyond annotations by disclosing the data source limitation: 'Inferred from competitor name/subtitle only — never their ranking algorithm,' which is important context about what the tool genuinely knows and what it cannot reveal.
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 two sentences, front-loads the read-only nature and core purpose, and every clause carries specific information: competitor visibility, missing targeting, top-50 ranking condition, winnability sorting, and inference limitations. 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?
With no output schema, the description still tells the agent what kind of results to expect: ranked keyword gap terms with winnability ordering. Combined with complete parameter documentation and safety annotations, the context is sufficient for correct invocation, though the exact response shape and count are not specified.
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 every parameter already has meaningful documentation. The tool description does not add parameter-level detail beyond what the schema provides, which meets the baseline but does not exceed it.
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 precisely defines what the tool returns: keyword opportunities based on terms competitors visibly use, that the app neither targets nor ranks top-50 for, sorted by winnability. It clearly differentiates itself from sibling tools like rank_check and competitor_watch by focusing on the visibility gap rather than direct ranking data.
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—find content/ASO opportunities competitors have that this app is missing—but does not explicitly state when to choose this over alternatives. It gives no exclusion criteria or sibling comparisons, leaving the routing decision partly to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are largely distinct by store, ownership, and analysis focus, with clear separation between App Store audits, Play audits, competitor diffs, keyword gaps, localization, rank checks, screenshots, and proof. A minor overlap exists between audit_app and preview_app, both of which read App Store listing data, though their outputs differ enough to avoid serious confusion.
All names use snake_case and are readable, but the grammatical pattern is mixed: some are verb_noun (audit_app, propose_copy), some are noun phrases (keyword_gaps, localization_gaps, war_room), and a few are bare nouns (proof). There is no consistent verb-first or noun-first convention across the set.
Twelve tools is well-scoped for an ASO intelligence server. Each tool addresses a meaningful part of the domain—auditing, competitor tracking, keyword/localization opportunities, rank checking, screenshot scoring, and proof—without feeling bloated or redundant.
The surface covers the core read-only ASO workflow: listing audits for both stores, owner-only Play audit, competitor monitoring, keyword and localization gaps, rank checks, screenshot coverage, draft copy proposals, and aggregate proof. The deliberate absence of write/publish tools is consistent with the server's stated human-approved loop, so no critical lifecycle gaps remain.